電腦網路通常將資料容量較大且持續時間較長的流稱為大象流。由於多個大象流佔用相同網路鏈路會造成網路擁塞，降低網路性能和服務品質，偵測大象流對電腦網路的性能管理和資源優化非常關鍵。軟體定義網路（Software-defined networking）是一種新型的網路架構。該架構將網路管理與資料轉發功能解耦，提供了新機制對網路進行全域管理和優化。本論文研究基於軟體定義架構的電腦網路上的通用大象流偵測方法，旨在通過研究資料包的採樣，大象流的建模，和網路的優化方法使得軟體定義網路控制器可以進行準確、穩定和高效的大象流偵測。本論文首先研究了軟體定義網路上資料包的採樣並提出使用流表項失效時間對轉發到控制器的包進行採樣，從而使控制器可以根據收到的包對大象流進行偵測。這種方法徹底避免了將交換機流表項保存的統計資訊直接轉發到控制器導致控制通道頻寬佔用過大的問題，使得控制器在進行大象流偵測時可以避免佔用過多網路資源。其次研究了大象流的建模，提出了三個大象流模型（ModelA、ModelB、和ModelC），並對模型的精度和穩定性進行了分析。由於使用控制器自己生成的網路統計資訊對大象流進行偵測將流表項失效時間與大象流偵測精度、流表大小以及控制通道頻寬佔用等多個網路性能指標耦合在一起，本論文構建並求解了一個多目標優化方程，旨在尋找最優的流表項失效時間對大象流偵測精度、流表大小、控制通道頻寬佔用進行聯合優化。本論文最後提出了兩個方案對流表項失效時間進行優化。第一個方案使用ModelA 對大象流進行準確和穩定的偵測。該方案構建了一個三目標優化方程聯合優化大象流偵測精度、大象流偵測時效性、和控制通道頻寬佔用。該三目標優化方程通過加權轉化為一個單目標優化方法並通過貝葉斯優化法（Bayesian Optimization）求解得到最佳的流表項失效時間和變化率。第二個方案使用ModelB 和ModelC 構造半監督學習法（cotraining），再與強化學習法（Reinforcement learning）相結合在軟體定義網路上實現了對大象流準確、穩定、和高效的偵測。這個方案利用了ModelC 的高效率，並通過ModelB 不斷地將部分無標籤的測試資料包轉化為有標籤的訓練資料包，對ModelC 進行持續再訓練，有效地提高了ModelC 偵測精度和穩定性。ModelB在轉化過程中所消耗的控制通道頻寬通過強化學習構建的獎勵方程進行控制，從而使控制器可以使用交換機轉發的資料包實現對大象流準確、穩定、高效的偵測。
本論文所有工作都在開源平臺上，使用Python 語言程式設計實現，並通過模擬進行功能和性能的評估。儘管模擬方法具有一定的局限性，本論文最後分析和討論了如何將這些採樣、建模、偵測、和優化方法進一步推廣到實際的軟體定義網路和不同應用場景中。

Elephants flows (elephants) are big flows with long time duration and large byte/packet counts. It is significant to classify elephants over computer networks, as two elephants sharing the same link can cause network congestion and degrade network performance and Quality of Service (QOS). Since Software-Defined Networking (SDN) decouples network control from the data plane, it can facilitate computer networks with new primitives to enable network-wide management and optimization. This thesis studies the general elephant classification methods over SDN computer networks, aiming to provide accurate, efficient, and stable elephant classification solutions at controllers by investigating the sampling, modeling, and optimizing mechanisms for elephant classification. Packet sampling over SDN systems is studied firstly. Packets of flows sampled by the timeouts of flow entries are proposed to classify elephants. It completely avoids moving statistics dedicated for elephant classification from switches to controllers and can achieve a high classification accuracy. Secondly, the models describing elephants are studied. Three elephant models (ModelA, ModelB, and ModelC) are provided. Their accuracy and stability are investigated. Thirdly, a multiobjective optimization problem is generalized and solved, aiming to find the best timeout set that jointly maximizes the classification accuracy and resource efficiency when the flows being classified are sampled by the timeouts of flow entries. Finally, the elephant classification time efficiency is highlighted. Two approaches are proposed. The first involves ModelA for its high accuracy and stability and formulates a multi-objective problem to optimize the classification accuracy, resource efficiency, and time efficiency. The Bayesian Optimization (BO) and a novel timeout adjustment strategy are applied for the problem solving. The second involves ModelB and ModelC together with co-training and Reinforcement Learning (RL) to achieve the accurate, stable, and efficient elephant classification over SDN computer networks. While ModelC improves its general accuracy by being periodically retrained over the flows labeled by ModelB online, ModelB manages its control channel bandwidth usage through a reward function formulated using RL.
All these works are programmed in Python, prototyped over open sourced platforms and algorithms, and evaluated over simulation. Although the approaches proposed have their limitations, potentials are discussed in extending them to various networking scenarios or over physical SDN systems.

1 Introduction and Background 1
1.1 Computer Networks and SDN Architecture 7
1.1.1 Transmission Control Protocol/Internet Protocol Architecture 7
1.1.2 Conventional Computer Networks 8
1.1.3 SDN Architecture and Major Components 8
1.1.4 Summary 12
1.2 Flows and Elephants 12
1.2.1 Flows 13
1.2.2 Metadata of Flows 13
1.2.3 Elephants 14
1.3 Statistics 15
1.3.1 Statistics Collection 15
1.3.2 Statistics Sampling 17
1.3.3 Statistics Processing 18
1.4 Technologies Involved in Elephant Modeling, Classification, and Optimization 20
1.4.1 Statistical Analysis 20
1.4.2 Machine Learning 22
1.4.3 Evolutionary Algorithms 24
1.5 Metrics 25
1.5.1 Performance Metrics for Models, Classifiers, and Algorithms 25
1.5.2 Time Efficiency 27
1.5.3 Stability 28
1.5.4 Performance Metrics for SDN Computer Networks 28
1.6 Tools and Data Sets 29
1.6.1 Simulation Tools 30
1.6.2 Tools for Data Sets 31
1.6.3 Testbed for Simulation 32
1.7 Research Questions and Challenges 32
1.7.1 Packet Sampling Using Flow Entry Timeouts for Elephant Classification 33
1.7.2 Modeling Elephants 35
1.7.3 Optimizing Timeouts Using Multi-objective Optimization Problems 36
1.7.4 Adjusting Timeouts for Accurate and Stable Elephant Flows Classification 38
1.7.5 Toward Accurate, Time Efficient, and Stable Elephant Flows Classification 39
1.8 Contribution 39
2 Packet Sampling Using Flow Entry Timeouts for Elephant Flows Classification 43
2.1 Introduction 43
2.2 Background and Related Work 44
2.2.1 Timeouts of Flow Entries 44
2.2.2 Timeout Configuration and Optimization 47
2.2.3 Network Statistics Collection 49
2.2.4 Elephants Classification 50
2.3 Applying Timeout of Flow Entries to Sample Packets for Elephant Classification 51
2.4 Feasibility Evaluation 52
2.5 Conclusion 54
3 Modeling Elephant Flows 55
3.1 Introduction 55
3.2 Background and Related Work 55
3.2.1 Metadata Used to Model Elephants 55
3.2.2 Methods Enabling Elephant Modeling 58
3.2.3 Summary 63
3.3 Modeling Elephant Flows 64
3.3.1 Training Data Set Labeling and Analyzing 64
3.3.2 Elephant Modeling 66
3.4 Performance Evaluation 73
3.5 Conclusion 75
4 Optimizing Timeouts Using Multi-objective Optimization Problems 77
4.1 Introduction 77
4.2 Background and Related Work 78
4.2.1 Single Objective 78
4.2.2 Multiple Objectives 82
4.2.3 Algorithms 84
4.3 Multi-objective Optimization Problem Formulation 86
4.3.1 Modeling Control Channel Bandwidth Usage 88
4.3.2 Modeling Flow Table Size 88
4.3.3 Modeling Elephant Classification Inaccuracy 89
4.3.4 Multi-objective Optimization Problem Formulation 90
4.4 Solving Optimization Problem 90
4.4.1 Timeout Adjustment Strategies 90
4.4.2 Solving Problems 93
4.5 Evaluation 96
4.5.1 Optimizing Classification Inaccuracy and Control Channel Bandwidth Usage 97
4.5.2 Optimizing Flow Table Size and Control Channel Bandwidth Usage 98
4.5.3 Sensitivity Analysis 98
4.5.4 Improvement 103
4.6 Conclusion 104
5 Adjusting Timeouts for Accurate and Stable Elephant Classification 109
5.1 Introduction 109
5.2 Background and Related Work 110
5.2.1 Elephant Classification Solutions with Time Efficiency 111
5.2.2 Applications of BO 111
5.3 Elephant Model Used 113
5.4 Timeout Adjustment Strategy 114
5.5 Multi-objective Optimization Problem Formulation 115
5.6 Solving Optimization Problem 117
5.7 Evaluation 121
5.7.1 Stability 122
5.7.2 Sensitive analysis 123
5.7.3 Performance of BO 127
5.7.4 Discussion 128
5.8 Conclusion 132
6 Toward Accurate, Time Efficient, and Stable Elephant Classification 135
6.1 Introduction 135
6.2 Background and Related Work 139
6.2.1 Elephant Classification Solutions with Time Efficiency 139
6.2.2 Semi-supervised Learning in Elephant Classification 140
6.2.3 Applying RL in Elephant Classification 141
6.3 General Accuracy of ModelC 142
6.4 Combining Co-training and RL for Elephant Classification 144
6.4.1 Approach Overview 145
6.4.2 Co-training 147
6.4.3 RL 148
6.4.4 Overall Algorithm Combining Co-training and RL 151
6.5 Evaluation 155
6.5.1 Time Cost in Training ModelC 155
6.5.2 Overhead of ModelB 156
6.5.3 Estimating the Proposed Approach 159
6.5.4 Sensitive Analysis 162
6.5.5 Discussion 165
6.6 Conclusion 170
7 Conclusions and Future Work 173
7.1 Conclusions 173
7.2 Suggestions for Future Works 179
7.2.1 Modeling Elephants Using Context Metadata of Flows 179
7.2.2 Extending Elephant Classification over Out of Distribution (OOD) Testing Data Sets 181
7.2.3 Implementing Elephant Classifiers in Controller Solutions 182
7.2.4 Extending Elephant Classification in Various Networking Scenarios with Other Technologies 183
References 185

[1] J. F. Kurose and K. W. Ross, Computer networking: A top-down approach, 4/E. Pearson Addision Wesley, 4 ed., 2007.
[2] F. Pacheco, E. Exposito, M. Gineste, C. Baudoin, and J. Aguilar, “Towards the deployment of machine learning solutions in network traffic classification: A systematic survey,” IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1988–2014, 2018.
[3] U. Deshpande, N. Rajesh, and S. Dhananjaya, “Survey of sdn traffic flow classification approaches,” INFOCOMP Journal of Computer Science, vol. 20, no. 1, 2021.
[4] A. Callado, C. Kamienski, G. Szab´o, B. P. Gero, J. Kelner, S. Fernandes, and D. Sadok, “A survey on internet traffic identification,” IEEE communications surveys & tutorials, vol. 11, no. 3, pp. 37–52, 2009.
[5] K. Kirkpatrick, “Software-defined networking,” Communications of the ACM, vol. 56, no. 9, pp. 16–19, 2013.
[6] F. Bannour, S. Souihi, and A. Mellouk, “Distributed sdn control: Survey, taxonomy, and challenges,” IEEE Communications Surveys & Tutorials, vol. 20, no. 1, pp. 333–354, 2017.
[7] S. Ahmad and A. H. Mir, “Scalability, consistency, reliability and security in sdn controllers: A survey of diverse sdn controllers,” Journal of Network and Systems Management, vol. 29, no. 1, pp. 1–59, 2021.
[8] A. R. Curtis, J. C. Mogul, J. Tourrilhes, P. Yalagandula, P. Sharma, and S. Banerjee, “Devoflow: Scaling flow management for high-performance networks,” in Proceedings of the ACM SIGCOMM 2011 Conference, pp. 254–265, Toronto, ON, Canada, August 15–19, 2011.
[9] M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, A. Vahdat, et al., “Hedera: dynamic flow scheduling for data center networks.,” in Nsdi, vol. 10, pp. 89–92, San Jose, CA, USA, April 28–30, 2010.
[10] M. Wang, B. Li, and Z. Li, “sflow: Towards resource-efficient and agile service federation in service overlay networks,” in 24th International Conference on Distributed Computing Systems, 2004. Proceedings., pp. 628–635, Hachioji, Tokyo, Japan, March 24–26, 2004.
[11] B. Claise, G. Sadasivan, V. Valluri, and M. Djernaes, “Cisco systems netflow services export version 9,” 2004.
[12] N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner, “Openflow: enabling innovation in campus networks,” ACM SIGCOMM computer communication review, vol. 38, no. 2, pp. 69–74, 2008.
[13] P. V. Mockapetris, “Rfc1034: Domain names-concepts and facilities,” 1987.
[14] E. Kaljic, A. Maric, P. Njemcevic, and M. Hadzialic, “A survey on data plane flexibility and programmability in software-defined networking,” IEEE Access, vol. 7, pp. 47804–47840, 2019.
[15] M. Baca, Introduction to metadata. Getty Publications, 2016.
[16] R. Harrison, S. L. Feibish, A. Gupta, R. Teixeira, S. Muthukrishnan, and J. Rexford, “Carpe elephants: Seize the global heavy hitters,” in Proceedings of the Workshop on Secure Programmable Network Infrastructure, pp. 15–21, Virtual Event, USA, August 14–14, 2020.
[17] J. Moraney and D. Raz, “On the practical detection of the top-k flows,” in 2018 14th International Conference on Network and Service Management (CNSM), pp. 81–89, Rome, Italy, November 5–9, 2018.
[18] R. Jang, D. Min, S. Moon, D. Mohaisen, and D. Nyang, “Sketchflow: Per-flow systematic sampling using sketch saturation event,” in IEEE INFOCOM 2020-IEEE Conference on Computer Communications, pp. 1339–1348, Toronto, ON, Canada, July 7–9, 2020.
[19] F. Tang, H. Zhang, L. T. Yang, and L. Chen, “Elephant flow detection and differentiated scheduling with efficient sampling and classification,” IEEE Transactions on Cloud Computing, 2019.
[20] C. M. Musil, C. B. Warner, P. K. Yobas, and S. L. Jones, “A comparison of imputation techniques for handling missing data,” Western Journal of Nursing Research, vol. 24, no. 7, pp. 815–829, 2002.
[21] S. Van Buuren, Flexible imputation of missing data. CRC press, 2018.
[22] W. J. Dixon and F. J. Massey Jr, “Introduction to statistical analysis.,” 1951.
[23] T. W. Anderson, The statistical analysis of time series, vol. 19. John Wiley & Sons, 2011.
[24] S. Brooks, A. Gelman, G. Jones, and X.-L. Meng, Handbook of markov chain monte carlo. CRC press, 2011.
[25] S. V. Kumar and L. Vanajakshi, “Short-term traffic flow prediction using seasonal arima model with limited input data,” European Transport Research Review, vol. 7, no. 3, pp. 1–9, 2015.
[26] G. A. Seber and A. J. Lee, Linear regression analysis, vol. 329. John Wiley & Sons, 2012.
[27] D. W. Hosmer Jr, S. Lemeshow, and R. X. Sturdivant, Applied logistic regression, vol. 398. John Wiley & Sons, 2013.
[28] P. Consul and F. Famoye, “Generalized poisson regression model,” Communications in Statistics-Theory and Methods, vol. 21, no. 1, pp. 89–109, 1992.
[29] I. Muhammad and Z. Yan, “Supervised machine learning approaches: A survey.,” ICTACT Journal on Soft Computing, vol. 5, no. 3, 2015.
[30] M. E. Celebi and K. Aydin, Unsupervised learning algorithms. Springer, 2016.
[31] X. J. Zhu, “Semi-supervised learning literature survey,” 2005.
[32] L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: A survey,” Journal of artificial intelligence research, vol. 4, pp. 237–285, 1996.
[33] J. F. Torres, D. Hadjout, A. Sebaa, F. Mart´ınez-A´ lvarez, and A. Troncoso, “Deep learning for time series forecasting: A survey,” Big Data, vol. 9, no. 1, pp. 3–21, 2021.
[34] K. Deb, “Multi-objective optimisation using evolutionary algorithms: an introduction,” in Multi-objective evolutionary optimisation for product design and manufacturing, pp. 3–34, Springer, 2011.
[35] M. D. Vose, The simple genetic algorithm: foundations and theory. MIT press, 1999.
[36] J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95-international conference on neural networks, vol. 4, pp. 1942–1948, Perth, WA, Australia, November 27–December 1, 1995.
[37] M. Dorigo, M. Birattari, and T. Stutzle, “Ant colony optimization,” IEEE computational intelligence magazine, vol. 1, no. 4, pp. 28–39, 2006.
[38] S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, “Optimization by simulated annealing,” science, vol. 220, no. 4598, pp. 671–680, 1983.
[39] K. Shang, H. Ishibuchi, L. He, and L. M. Pang, “A survey on the hypervolume indicator in evolutionary multiobjective optimization,” IEEE Transactions on Evolutionary Computation, vol. 25, no. 1, pp. 1–20, 2020.
[40] B. Lantz, B. Heller, and N. McKeown, “A network in a laptop: rapid prototyping for software-defined networks,” in Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks, pp. 1–6, Monterey, Canada, October 20–21, 2010.
[41] S.-Y. Wang, C.-L. Chou, and C.-M. Yang, “Estinet openflow network simulator and emulator,” IEEE Communications Magazine, vol. 51, no. 9, pp. 110–117, 2013.
[42] R. Sherwood and Y. Kok-Kiong, “Cbench: an open-flow controller benchmarker,” URL http://archive. openflow. org/wk/index. php/Oflops, 2010.
[43] C. Rotsos, N. Sarrar, S. Uhlig, R. Sherwood, and A. W. Moore, “Oflops: An open framework for openflow switch evaluation,” in International Conference on Passive and Active Network Measurement, Springer, pp. 85–95, Vienna, Austria, March 29–April 1, 2012.
[44] C.-H. Hsu and U. Kremer, “Iperf: A framework for automatic construction of performance prediction models,” in Workshop on Profile and Feedback-Directed Compilation (PFDC), Paris, France, October 13–13, 1998.
[45] A. Maria, “Introduction to modeling and simulation,” in Proceedings of the 29th conference on Winter simulation, pp. 7–13, Atlanta, Georgia, USA, December 7–10, 1997.
[46] J. M. Epstein, “Why model?,” Journal of artificial societies and social simulation, vol. 11, no. 4, p. 12, 2008.
[47] M. Rifai, N. Huin, C. Caillouet, F. Giroire, J. Moulierac, D. L. Pacheco, and G. Urvoy-Keller, “Minnie: An sdn world with few compressed forwarding rules,” Computer Networks, vol. 121, pp. 185–207, 2017.
[48] B. Isyaku, K. A. Bakar, M. S. M. Zahid, and M. Nura Yusuf, “Adaptive and hybrid idle–hard timeout allocation and flow eviction mechanism considering traffic characteristics,” Electronics, vol. 9, no. 11, p. 1983, 2020.
[49] H. Zhu, H. Fan, X. Luo, and Y. Jin, “Intelligent timeout master: Dynamic timeout for sdn-based data centers,” in 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM), pp. 734–737, Ottawa, Canada, May 15–17, 2015.
[50] L. Zhang, S. Wang, S. Xu, R. Lin, and H. Yu, “Timeoutx: An adaptive flow table management method in software defined networks,” in 2015 IEEE Global Communications Conference (GLOBECOM), pp. 1–6, San Diego, CA, USA, December 6–10, 2015.
[51] B. Sooden and M. R. Abbasi, “A dynamic hybrid timeout method to secure flow tables against ddos attacks in sdn,” in 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC), pp. 29–34, Jalandhar, India, December 15–17, 2018.
[52] Q. Li, N. Huang, D. Wang, X. Li, Y. Jiang, and Z. Song, “Hqtimer: a hybrid q-learning-based timeout mechanism in software-defined networks,” IEEE Transactions on Network and Service Management, vol. 16, no. 1, pp. 153–166, 2019.
[53] A. Panda, S. S. Samal, A. K. Turuk, A. Panda, and V. C. Venkatesh, “Dynamic hard timeout based flow table management in openflow enabled sdn,” in 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), pp. 1–6, Vellore, Tamilnadu, India, March 30–31, 2019.
[54] B. Kurt, A. T. Cemgil, G. K. Kurt, and E. Zeydan, “Estimating network flow length distributions via bayesian nonnegative tensor factorization,” Wireless Communications and Mobile Computing, vol. 2019, 2019.
[55] D. S. Terzi, R. Terzi, and S. Sagiroglu, “Big data analytics for network anomaly detection from netflow data,” in 2017 International Conference on Computer Science and Engineering (UBMK), pp. 592–597, Antalya, Turkey, October 5–8, 2017.
[56] C. Hu, B. Liu, H. Zhao, K. Chen, Y. Chen, Y. Cheng, and H. Wu, “Discount counting for fast flow statistics on flow size and flow volume,” IEEE/ACM Transactions on Networking, vol. 22, no. 3, pp. 970–981, 2013.
[57] A. R. Curtis, W. Kim, and P. Yalagandula, “Mahout: Low-overhead datacenter traffic management using end-host-based elephant detection,” in 2011 Proceedings IEEE INFOCOM, pp. 1629–1637, Shanghai, China, April 10–15, 2011.
[58] M. Zhao, M. Li, L. Mei, and Y. Tian, “Flowwatcher: Adaptive flow counting for source routing over protocol independent sdn networks,” in 2018 8th International Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 237–242, Beijing, China, June 15–17, 2018.
[59] B. Wang, J. Su, J. Li, and B. Han, “Effiview: Trigger-based monitoring approach with low cost in sdn,” in 2017 IEEE 19th International Conference on High Performance Computing and Communications; IEEE 15th International Conference on Smart City; IEEE 3rd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 309–315, Beijing, China, December 18–20, 2017.
[60] A. AlGhadhban and B. Shihada, “Flight: A fast and lightweight elephant-flow detection mechanism,” in 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS), pp. 1537–1538, Vienna, Austria, July 2–5, 2018.
[61] M. Hamdan, B. Mohammed, U. Humayun, A. Abdelaziz, S. Khan, M. A. Ali, M. Imran, and M. N. Marsono, “Flow-aware elephant flow detection for software-defined networks,” IEEE Access, vol. 8, pp. 72585–72597, 2020.
[62] T. Mori, M. Uchida, R. Kawahara, J. Pan, and S. Goto, “Identifying elephant flows through periodically sampled packets,” in Proceedings of the 4th ACM SIGCOMM conference on Internet measurement, pp. 115–120, Taormina Sicily, Italy, October 25–27, 2004.
[63] M. Afaq, S. Rehman, and W.-C. Song, “Large flows detection, marking, and mitigation based on sflow standard in sdn,” Journal of Korea Multimedia Society, vol. 18, no. 2, pp. 189–198, 2015.
[64] Y. Afek, A. Bremler-Barr, S. L. Feibish, and L. Schiff, “Detecting heavy flows in the sdn match and action model,” Computer Networks, vol. 136, pp. 1–12, 2018.
[65] P. Xiao, W. Qu, H. Qi, Y. Xu, and Z. Li, “An efficient elephant flow detection with cost-sensitive in sdn,” in 2015 1st International Conference on Industrial Networks and Intelligent Systems (INISCom), pp. 24–28, Tokyo, Japan, March 2–4, 2015.
[66] J. Mazel, R. Fontugne, and K. Fukuda, “A taxonomy of anomalies in backbone
network traffic,” in 2014 international wireless communications and mobile computing conference (IWCMC), pp. 30–36, Nicosia, Cyprus, August 4–8, 2014.
[67] T. Pan, X. Guo, C. Zhang, J. Jiang, H. Wu, and B. Liuy, “Tracking millions of flows in high speed networks for application identification,” in 2012 Proceedings IEEE INFOCOM, pp. 1647–1655, Orlando, FL, USA, March 25–30, 2012.
[68] X. Li and C. Qian, “Low-complexity multi-resource packet scheduling for network function virtualization,” in 2015 IEEE Conference on Computer Communications (INFOCOM), pp. 1400–1408, Hong Kong, China, April 26–May 1, 2015.
[69] M. Kallitsis, S. A. Stoev, S. Bhattacharya, and G. Michailidis, “Amon: An open source architecture for online monitoring, statistical analysis, and forensics of multi-gigabit streams,” IEEE Journal on Selected Areas in Communications, vol. 34, no. 6, pp. 1834–1848, 2016.
[70] F. Raspall and S. Sallent, “Adaptive shared-state sampling,” in Proceedings of the 8th ACM SIGCOMM conference on Internet measurement, pp. 271–284, Vouliagmeni, Greece, October 20–22, 2008.
[71] S. Dashti, M. Berenjkoub, and A. Tahmasbi, “An efficient sketch-based framework to identify multiple heavy-hitters and its application in dos detection,” in 2014 22nd Iranian Conference on Electrical Engineering (ICEE), pp. 1113–1118, Tehran, Iran, May 20–22, 2014.
[72] E. T. B. Hong and C. Y. Wey, “An optimized flow management mechanism in openflow network,” in 2017 International Conference on Information Networking (ICOIN), pp. 143–147, Da Nang, January 11–13, 2017.
[73] M. A. da Cruz, L. C. e Silva, S. Correa, and K. V. Cardoso, “Accurate online detection of bidimensional hierarchical heavy hitters in software-defined networks,” in 2013 IEEE Latin-America Conference on Communications, pp. 1–6, Alagoas, Brazil, December 9–10, 2013.
[74] B.-S. Lee, R. Kanagavelu, and K. M. M. Aung, “An efficient flow cache algorithm with improved fairness in software-defined data center networks,” in 2013 IEEE 2nd International Conference on Cloud Networking (CloudNet), pp. 18–24, San Francisco, CA, USA, November 11–13, 2013.
[75] J. Wallerich, H. Dreger, A. Feldmann, B. Krishnamurthy, and W. Willinger, “A methodology for studying persistency aspects of internet flows,” ACM SIGCOMM Computer Communication Review, vol. 35, no. 2, pp. 23–36, 2005.
[76] L. Peng, B. Yang, and Y. Chen, “Effective packet number for early stage internet traffic identification,” Neurocomputing, vol. 156, pp. 252–267, 2015.
[77] L. Bernaille, R. Teixeira, I. Akodkenou, A. Soule, and K. Salamatian, “Traffic classification on the fly,” ACM SIGCOMM Computer Communication Review, vol. 36, no. 2, pp. 23–26, 2006.
[78] N.-F. Huang, G.-Y. Jai, and H.-C. Chao, “Early identifying application traffic with application characteristics,” in 2008 IEEE International Conference on Communications, pp. 5788–5792, Beijing, China, May 19–23, 2008.
[79] R.-H. Hwang, M.-C. Peng, C.-W. Huang, P.-C. Lin, and V.-L. Nguyen, “An unsupervised deep learning model for early network traffic anomaly detection,” IEEE Access, vol. 8, pp. 30387–30399, 2020.
[80] B. Hull´ar, S. Laki, and A. Gyorgy, “Early identification of peer-to-peer traffic,” in 2011 IEEE International Conference on Communications (ICC), pp. 1–6, Kyoto, Japan, June 5–9, 2011.
[81] T. T. Nguyen, G. Armitage, P. Branch, and S. Zander, “Timely and continuous machine-learning-based classification for interactive ip traffic,” IEEE/ACM Transactions On Networking, vol. 20, no. 6, pp. 1880–1894, 2012.
[82] A. Rizzi, S. Colabrese, and A. Baiocchi, “Low complexity, high performance neuro-fuzzy system for internet traffic flows early classification,” in 2013 9th International Wireless Communications and Mobile Computing Conference (IWCMC), pp. 77–82, Sardinia, Italy, July 1–5, 2013.
[83] B. Pf¨ulb, C. Hardegen, A. Gepperth, and S. Rieger, “A study of deep learning for network traffic data forecasting,” in International Conference on Artificial Neural Networks,Springer, pp. 497–512, Munich, Germany, September 17–19, 2019.
[84] P. Poupart, Z. Chen, P. Jaini, F. Fung, H. Susanto, Y. Geng, L. Chen, K. Chen, and H. Jin, “Online flow size prediction for improved network routing,” in 2016 IEEE 24th International Conference on Network Protocols (ICNP), pp. 1–6, Singapore, Novenber 8–11, 2016.
[85] D. Comaneci and C. Dobre, “Securing networks using sdn and machine learning,” in 2018 IEEE International Conference on Computational Science and Engineering (CSE), pp. 194–200, Bucharest, Romania, October 29–31, 2018.
[86] S. T. V. Pasca, S. S. P. Kodali, and K. Kataoka, “Amps: Application aware multipath flow routing using machine learning in sdn,” in 2017 Twenty-third National Conference on Communications (NCC), pp. 1–6, Chennai, India, March 2–4, 2017.
[87] H. Kim, K. C. Claffy, M. Fomenkov, D. Barman, M. Faloutsos, and K. Lee, “Internet traffic classification demystified: myths, caveats, and the best practices,” in Proceedings of the 2008 ACM CoNEXT conference, pp. 1–12, Madrid, Spain, December 9–12, 2008.
[88] T. St¨ober, M. Frank, J. Schmitt, and I. Martinovic, “Who do you sync you are? smartphone fingerprinting via application behaviour,” in Proceedings of the sixth ACM conference on Security and privacy in wireless and mobile networks, pp. 7–12, Budapest, Hungary, August 17–19, 2013.
[89] L. Vu, C. T. Bui, and Q. U. Nguyen, “A deep learning based method for handling imbalanced problem in network traffic classification,” in Proceedings of the Eighth International Symposium on Information and Communication Technology, pp. 333–339, Nha Trang, Vietnam, December 7–8, 2017.
[90] W. Wang, M. Zhu, J. Wang, X. Zeng, and Z. Yang, “End-to-end encrypted traffic classification with one-dimensional convolution neural networks,” in 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), pp. 43–48, Beijing, China, July 22–24, 2017.
[91] Z. Chen, K. He, J. Li, and Y. Geng, “Seq2img: A sequence-to-image based approach towards ip traffic classification using convolutional neural networks,” in 2017 IEEE International conference on big data (big data), pp. 1271–1276, Boston, MA, USA, December 11–14, 2017.
[92] M. Lotfollahi, M. J. Siavoshani, R. S. H. Zade, and M. Saberian, “Deep packet: A novel approach for encrypted traffic classification using deep learning,” Soft Computing, vol. 24, no. 3, pp. 1999–2012, 2020.
[93] Q. Wang, A. Yahyavi, B. Kemme, and W. He, “I know what you did on your smartphone: Inferring app usage over encrypted data traffic,” in 2015 IEEE conference on communications and network security (CNS), pp. 433–441, San Francisco, CA, USA, October 29–31, 2015.
[94] V. F. Taylor, R. Spolaor, M. Conti, and I. Martinovic, “Appscanner: Automatic fingerprinting of smartphone apps from encrypted network traffic,” in 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 439–454, Saarbruchen, Germany, March 21–24, 2016.
[95] A. Este, F. Gringoli, and L. Salgarelli, “Support vector machines for tcp traffic classification,” Computer Networks, vol. 53, no. 14, pp. 2476–2490, 2009.
[96] R. Yuan, Z. Li, X. Guan, and L. Xu, “An svm-based machine learning method for accurate internet traffic classification,” Information Systems Frontiers, vol. 12, no. 2, pp. 149–156, 2010.
[97] M. Hayes, B. Ng, A. Pekar, and W. K. Seah, “Scalable architecture for sdn traffic classification,” IEEE Systems Journal, vol. 12, no. 4, pp. 3203–3214, 2017.
[98] V. D’Alessandro, B. Park, L. Romano, C. Fetzer, et al., “Scalable network traffic classification using distributed support vector machines,” in 2015 IEEE 8th International Conference on Cloud Computing, pp. 1008–1012, London, UK, June 8–12, 2015.
[99] A. W. Moore and D. Zuev, “Internet traffic classification using bayesian analysis techniques,” in Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, pp. 50–60, Baff, Alberta, Canada, June 6–10, 2005.
[100] D. Herrmann, R. Wendolsky, and H. Federrath, “Website fingerprinting: attacking popular privacy enhancing technologies with the multinomial na¨ıve-bayes classifier,” in Proceedings of the 2009 ACM workshop on Cloud computing security, pp. 31–42, Chicago, IL, USA, November 13–13, 2009.
[101] J. H¨ochst, L. Baumg¨artner, M. Hollick, and B. Freisleben, “Unsupervised traffic flow classification using a neural autoencoder,” in 2017 IEEE 42Nd Conference on local computer networks (LCN), pp. 523–526, Singapore, October 9–12, 2017.
[102] P. Li, Z. Chen, L. T. Yang, J. Gao, Q. Zhang, and M. J. Deen, “An improved stacked auto-encoder for network traffic flow classification,” IEEE Network, vol. 32, no. 6, pp. 22–27, 2018.
[103] G. G´omez, P. Kotzias, M. Dell’Amico, L. Bilge, and J. Caballero, “Unsupervised detection and clustering of malicious tls flows,” arXiv preprint arXiv:2109.03878, 2021.
[104] X. Li, F. Qi, D. Xu, and X.-s. Qiu, “An internet traffic classification method based on semi-supervised support vector machine,” in 2011 IEEE International conference on communications (ICC), pp. 1–5, Kyoto, Japan, June 5–9, 2011.
[105] J. Yan, X. Yun, Z. Wu, H. Luo, S. Zhang, S. Jin, and Z. Zhang, “Online traffic classification based on co-training method,” in 2012 13th International Conference on Parallel and Distributed Computing, Applications and Technologies, pp. 391–397, Beijing, China, December 12–16, 2012.
[106] H. He, C. Che, F. Ma, J. Zhang, and X. Luo, “Traffic classification using en-semble learning and co-training,” WSEAS Proc. of the 8th AIC’08, pp. 458–463, 2008.
[107] S. Zhao, Y. Zhang, and P. Chang, “Network traffic classification using tri-training based on statistical flow characteristics,” in 2017 IEEE Trustcom/BigDataSE/ICESS, pp. 323–330, Sydney, Australia, August 1–4, 2017.
[108] P. Wang, S.-C. Lin, and M. Luo, “A framework for qos-aware traffic classification using semi-supervised machine learning in sdns,” in 2016 IEEE International conference on services computing (SCC), pp. 760–765, Kuala, Lumpour, Malaysia, May 23–27, 2016.
[109] J. Deng, H. Cai, and X. Wang, “Improved flow awareness by intelligent collaborative sampling in software defined networks,” in International Conference on 5G for Future Wireless Networks,Springer, pp. 182–194, Changsha, China, Februar 23–24, 2019.
[110] N. C. Luong, D. T. Hoang, S. Gong, D. Niyato, P. Wang, Y.-C. Liang, and D. I. Kim, “Applications of deep reinforcement learning in communications and networking: A survey,” IEEE Communications Surveys & Tutorials, vol. 21, no. 4, pp. 3133–3174, 2019.
[111] Y. He, Z. Zhang, and Y. Zhang, “A big data deep reinforcement learning approach to next generation green wireless networks,” in GLOBECOM 2017-2017 IEEE Global Communications Conference, pp. 1–6, Singapore, December 4–8, 2017.
[112] S. Rezaei and X. Liu, “Deep learning for encrypted traffic classification: An overview,” IEEE communications magazine, vol. 57, no. 5, pp. 76–81, 2019.
[113] L. Chen, J. Lingys, K. Chen, and X. Liao, “Datacenter traffic optimization with deep reinforcement learning,” Communication Networks and Service Management in the Era of Artificial Intelligence and Machine Learning, pp. 223–259, 2021.
[114] A. Blum and T. Mitchell, “Combining labeled and unlabeled data with co-training,” in Proceedings of the eleventh annual conference on Computational learning theory, pp. 92–100, Madison, Wisconsin, USA, July 24–26, 1998.
[115] Z.-H. Zhou and M. Li, “Tri-training: Exploiting unlabeled data using three classifiers,” IEEE Transactions on knowledge and Data Engineering, vol. 17, no. 11, pp. 1529–1541, 2005.
[116] L. G´omez-Chova, G. Camps-Valls, J. Munoz-Mari, and J. Calpe, “Semisupervised image classification with laplacian support vector machines,” IEEE Geoscience and Remote Sensing Letters, vol. 5, no. 3, pp. 336–340, 2008.
[117] C. Yu, J. Lan, J. Xie, and Y. Hu, “Qos-aware traffic classification architecture using machine learning and deep packet inspection in sdns,” Procedia computer science, vol. 131, pp. 1209–1216, 2018.
[118] Z. Zhang, L. Ma, K. K. Leung, L. Tassiulas, and J. Tucker, “Q-placement: Reinforcement-learning-based service placement in software-defined networks,” in 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS), pp. 1527–1532, Vienna, Austrial, July 2–5, 2018.
[119] L. S. Sampaio, P. H. Faustini, A. S. Silva, L. Z. Granville, and A. Schaeffer-Filho, “Using nfv and reinforcement learning for anomalies detection and mitigation in sdn,” in 2018 IEEE Symposium on Computers and Communications (ISCC), pp. 00432–00437, Natal, Brazil, June 25–28, 2018.
[120] T.-Y. Mu, A. Al-Fuqaha, K. Shuaib, F. M. Sallabi, and J. Qadir, “Sdn flow entry management using reinforcement learning,” ACM Transactions on Autonomous and Adaptive Systems (TAAS), vol. 13, no. 2, pp. 1–23, 2018.
[121] B. Isyaku, M. S. Mohd Zahid, M. Bte Kamat, K. Abu Bakar, and F. A. Ghaleb, “Software defined networking flow table management of openflow switches performance and security challenges: A survey,” Future Internet, vol. 12, no. 9, p. 147, 2020.
[122] T.-H. Tsai, K. Wang, and T.-Y. Chao, “Dynamic flow aggregation in sdns for application-aware routing,” in 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP), pp. 1–5, Pargue, Czech Republic, July 20–22, 2016.
[123] S. Luo, H. Yu, et al., “Fast incremental flow table aggregation in sdn,” in 2014 23rd International Conference on Computer Communication and Networks (ICCCN), pp. 1–8, Shanghai, China, August 4–7, 2014.
[124] C. Wang and H. Y. Youn, “Entry aggregation and early match using hidden markov model of flow table in sdn,” Sensors, vol. 19, no. 10, p. 2341, 2019.
[125] C. R. Meiners, A. X. Liu, and E. Torng, “Bit weaving: A non-prefix approach to compressing packet classifiers in tcams,” IEEE/ACM Transactions on Networking,vol. 20, no. 2, pp. 488–500, 2011.
[126] B. Leng, L. Huang, C. Qiao, H. Xu, and X. Wang, “Ftrs: A mechanism for reducing
flow table entries in software defined networks,” Computer Networks, vol. 122,
pp. 1–15, 2017. → pages 79, 87
[127] Y. Kanizo, D. Hay, and I. Keslassy, “Palette: Distributing tables in software-defined networks,” in 2013 Proceedings IEEE INFOCOM, pp. 545–549, Turin, Italy, April 14–19, 2013.
[128] X.-N. Nguyen, D. Saucez, C. Barakat, and T. Turletti, “Officer: A general optimization framework for openflow rule allocation and endpoint policy enforcement,” in 2015 IEEE Conference on Computer Communications (INFOCOM), pp. 478–486, Hong Kong, China, April 26–May 1, 2015.
[129] J.-F. Huang, G.-Y. Chang, C.-F. Wang, and C.-H. Lin, “Heterogeneous flow table distribution in software-defined networks,” IEEE Transactions on Emerging Topics in Computing, vol. 4, no. 2, pp. 252–261, 2015.
[130] B. Yan, Y. Xu, and H. J. Chao, “Adaptive wildcard rule cache management for software-defined networks,” IEEE/ACM Transactions on Networking, vol. 26, no. 2, pp. 962–975, 2018.
[131] J.-P. Sheu and Y.-C. Chuo, “Wildcard rules caching and cache replacement algorithms in software-defined networking,” IEEE Transactions on Network and Service Management, vol. 13, no. 1, pp. 19–29, 2016.
[132] H. Li, S. Guo, C. Wu, and J. Li, “Fdrc: Flow-driven rule caching optimization in software defined networking,” in 2015 IEEE International Conference on Communications (ICC), pp. 5777–5782, London, UK, June 8–12, 2015.
[133] X. Li and Y. Huang, “A flow table with two-stage timeout mechanism for sdn switches,” in 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 1804–1809, Zhangjiajie, China, August 10–12, 2019.
[134] Y. Liu, B. Tang, D. Yuan, J. Ran, and H. Hu, “A dynamic adaptive timeout approach for sdn switch,” in 2016 2nd IEEE International Conference on Computer and Communications (ICCC), pp. 2577–2582, Chengdu, China, July 27–29, 2016.
[135] M. Lu, W. Deng, and Y. Shi, “Tf-idletimeout: Improving efficiency of tcam in sdn by dynamically adjusting flow entry lifecycle,” in 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 002681–002686, Budapest, Hungary, October 9–12, 2016.
[136] B. Isyaku, M. B. Kamat, K. bin Abu Bakar, M. S. M. Zahid, and F. A. Ghaleb, “Ihta: dynamic idle-hard timeout allocation algorithm based openflow switch,” in 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE), pp. 170–175, Penang, Malaysia, April 18–20, 2020.
[137] X. Xu, L. Hu, H. Lin, and Z. Fan, “An adaptive flow table adjustment algorithm for sdn,” in 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 1779–1784, Zhangjiajie, China, August 10–12, 2019.
[138] R. Challa, Y. Lee, and H. Choo, “Intelligent eviction strategy for efficient flow table management in openflow switches,” in 2016 IEEE NetSoft Conference and Workshops (NetSoft), pp. 312–318, Seoul, Korea, June 6–10, 2016.
[139] Z. Guo, R. Liu, Y. Xu, A. Gushchin, A. Walid, and H. J. Chao, “Star: Preventing flow-table overflow in software-defined networks,” Computer Networks, vol. 125, pp. 15–25, 2017.
[140] T. Koponen, M. Casado, N. Gude, J. Stribling, L. Poutievski, M. Zhu, R. Ramanathan, Y. Iwata, H. Inoue, T. Hama, et al., “Onix: A distributed control platform for large-scale production networks.,” in OSDI, vol. 10, pp. 1–6, Vancouver, BC, Canada, October 4–6, 2010.
[141] P. Berde, M. Gerola, J. Hart, Y. Higuchi, M. Kobayashi, T. Koide, B. Lantz, B. O’Connor, P. Radoslavov, W. Snow, et al., “Onos: towards an open, distributed sdn os,” in Proceedings of the third workshop on Hot topics in software defined networking, pp. 1–6, Chicago, IL, USA, August 22–22, 2014.
[142] J. Medved, R. Varga, A. Tkacik, and K. Gray, “Opendaylight: Towards a model-driven sdn controller architecture,” in Proceeding of IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks 2014, pp. 1–6, Sydney, Australia, Jun 19–19, 2014.
[143] T. Das, V. Sridharan, and M. Gurusamy, “A survey on controller placement in sdn,” IEEE communications surveys & tutorials, vol. 22, no. 1, pp. 472–503, 2019.
[144] M. Malboubi, L. Wang, C.-N. Chuah, and P. Sharma, “Intelligent sdn based traffic (de) aggregation and measurement paradigm (istamp),” in IEEE INFOCOM 2014-IEEE Conference on Computer Communications, pp. 934–942, Toronto, ON, Canada, April 27–May 2, 2014.
[145] G. A. Ajaeiya, N. Adalian, I. H. Elhajj, A. Kayssi, and A. Chehab, “Flow-based intrusion detection system for sdn,” in 2017 IEEE Symposium on Computers and Communications (ISCC), pp. 787–793, Heraklion, Greece, July 3–6, 2017.
[146] Q. T. Minh, T. K. Dang, T. Nam, T. Kitahara, et al., “Flow aggregation for sdn-based delay-insensitive traffic control in mobile core networks,” IET Communications, vol. 13, no. 8, pp. 1051–1060, 2019.
[147] W. Queiroz, M. A. Capretz, and M. Dantas, “An approach for sdn traffic monitoring based on big data techniques,” Journal of Network and Computer Applications, vol. 131, pp. 28–39, 2019.
[148] G. Yang, H. Jin, M. Kang, G. J. Moon, and C. Yoo, “Network monitoring for sdn virtual networks,” in IEEE INFOCOM 2020-IEEE Conference on Computer Communications, pp. 1261–1270, Toronto, ON, Canada, July 6–9, 2020.
[149] L. Liao, V. C. Leung, and M. Chen, “An efficient and accurate link latency monitoring method for low-latency software-defined networks,” IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 2, pp. 377–391, 2018.
[150] Y. Afek, A. Bremler-Barr, S. Landau Feibish, and L. Schiff, “Sampling and large flow detection in sdn,” in Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pp. 345–346, London, UK, August 17–21, 2015.
[151] R. Cohen and E. Moroshko, “Sampling-on-demand in sdn,” IEEE/ACM Transactions on Networking, vol. 26, no. 6, pp. 2612–2622, 2018.
[152] J. Suh, T. T. Kwon, C. Dixon, W. Felter, and J. Carter, “Opensample: A low-latency, sampling-based measurement platform for commodity sdn,” in 2014 IEEE 34th International Conference on Distributed Computing Systems, pp. 228–237, Madrid, Spain, June 30–July 3, 2014.
[153] L. X. Liao, H.-C. Chao, and M.-Y. Chen, “Intelligently modeling, detecting, and scheduling elephant flows in software defined energy cloud: A survey,” Journal of Parallel and Distributed Computing, vol. 146, pp. 64–78, 2020.
[154] Z. Shen, J. Liu, Y. He, X. Zhang, R. Xu, H. Yu, and P. Cui, “Towards out-of-distribution generalization: A survey,” arXiv preprint arXiv:2108.13624, 2021.
[155] D. Tammaro, S. Valenti, D. Rossi, and A. Pescap´e, “Exploiting packet-sampling measurements for traffic characterization and classification,” International Journal of Network Management, vol. 22, no. 6, pp. 451–476, 2012.
[156] V. Carela-Espa˜nol, P. Barlet-Ros, A. Cabellos-Aparicio, and J. Sol´e-Pareta, “Analysis of the impact of sampling on netflow traffic classification,” Computer Networks, vol. 55, no. 5, pp. 1083–1099, 2011.
[157] S. Xuan, D. Tang, I. Chung, Y. Cho, X. Du, and W. Yang, “Network traffic sampling system based on storage compression for application classification detection,” IEEE Access, vol. 8, pp. 63106–63120, 2020.
[158] C. MadhusudhanaRao and M. Naidu, “Flow sampling for network intrusion detection–an acceptance sampling approach,” International Journal of Applied Engineering Research, vol. 13, no. 13, pp. 11030–11034, 2018.
[159] R. M. A. Ujjan, Z. Pervez, K. Dahal, A. K. Bashir, R. Mumtaz, and J. Gonz´alez, “Towards sflow and adaptive polling sampling for deep learning based ddos detection in sdn,” Future Generation Computer Systems, vol. 111, pp. 763–779, 2020.
[160] J. Zhao and N. Liu, “Semi-supervised classification based mixed sampling for imbalanced data,” Open Physics, vol. 17, no. 1, pp. 975–983, 2019.
[161] A. Zarek, Y. Ganjali, and D. Lie, “Openflow timeouts demystified,” Univ. of Toronto, Toronto, Ontario, Canada, 2012.
[162] S. Shirali-Shahreza and Y. Ganjali, “Delayed installation and expedited eviction: An alternative approach to reduce flow table occupancy in sdn switches,” IEEE/ACM Transactions on Networking, vol. 26, no. 4, pp. 1547–1561, 2018.
[163] G. Zhao, H. Xu, S. Chen, L. Huang, and P. Wang, “Joint optimization of flow table and group table for default paths in sdns,” IEEE/ACM Transactions on Networking, vol. 26, no. 4, pp. 1837–1850, 2018.
[164] S. Q. Zhang, Q. Zhang, A. Tizghadam, B. Park, H. Bannazadeh, R. Boutaba, and A. Leon-Garcia, “Tcam space-efficient routing in a software defined network,” Computer Networks, vol. 125, pp. 26–40, 2017.
[165] Z. Guo, Y. Xu, R. Liu, A. Gushchin, K.-y. Chen, A. Walid, and H. J. Chao, “Balancing flow table occupancy and link utilization in software-defined networks,” Future Generation Computer Systems, vol. 89, pp. 213–223, 2018.
[166] Z. Li, Y. Hu, and X. Zhang, “Sdn flow entry adaptive timeout mechanism based on resource preference,” in IOP Conference Series: Materials Science and Engineering, vol. 569, p. 042018, Kazimierz Dolny, Poland, November 21–23, 2019.
[167] Y. Guo, H. Luo, Z. Wang, X. Yin, and J. Wu, “Routing optimization with path cardinality constraints in a hybrid sdn,” Computer Communications, vol. 165, pp. 112–121, 2021.
[168] M. K. Awad, M. El-Shafei, T. Dimitriou, Y. Rafique, M. Baidas, and A. Alhusaini, “Power-efficient routing for sdn with discrete link rates and size-limited flow tables: A tree-based particle swarm optimization approach,” International Journal of Network Management, vol. 27, no. 5, p. e1972, 2017.
[169] J. Gal´an-Jim´enez, J. Berrocal, J. L. Herrera, and M. Polverini, “Multi-objective genetic algorithm for the joint optimization of energy efficiency and rule reduction in software-defined networks,” in 2020 11th International Conference on Network of the Future (NoF), pp. 33–37, Bordeaux, France, October 12–14, 2020.
[170] V. Pereira, M. Rocha, and P. Sousa, “Hybrid ip/sdn routing for inter-data center communications,” in 2019 IEEE 8th International Conference on Cloud Networking (CloudNet), pp. 1–3, Coimbra, Portugal, November 4–6, 2019.
[171] B. Heller, R. Sherwood, and N. McKeown, “The controller placement problem,” ACM SIGCOMM Computer Communication Review, vol. 42, no. 4, pp. 473–478, 2012.
[172] J. Lu, Z. Zhang, T. Hu, P. Yi, and J. Lan, “A survey of controller placement problem in software-defined networking,” IEEE Access, vol. 7, pp. 24290–24307, 2019.
[173] H. Choi, S. M. Raza, M. Kim, and H. Choo, “Udp flow entry eviction strategy using q-learning in software defined networking,” in 2020 16th International Conference on Network and Service Management (CNSM), pp. 1–7, Izmir, Turkey, November 2–6, 2020.
[174] J. Mockus, V. Tiesis, and A. Zilinskas, “The application of bayesian methods for seeking the extremum,” Towards global optimization, vol. 2, no. 117-129, p. 2, 1978.
[175] N. Srinivas, A. Krause, S. M. Kakade, and M. Seeger, “Gaussian process optimization in the bandit setting: No regret and experimental design,” arXiv preprint arXiv:0912.3995, 2009.
[176] A. D. Bull, “Convergence rates of efficient global optimization algorithms.,” Journal of Machine Learning Research, vol. 12, no. 10, 2011.
[177] Q. Xiang, J. Zhang, K. Gao, Y.-s. Lim, F. Le, G. Li, and Y. R. Yang, “Toward optimal software-defined interdomain routing,” in IEEE INFOCOM 2020-IEEE Conference on Computer Communications, pp. 1529–1538, Toronto, ON, Canada, July 6–9, 2020.
[178] N. Khan, D. E. Goldberg, and M. Pelikan, “Multi-objective bayesian optimization algorithm,” in Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation, pp. 684–684, July 9–13, 2002.
[179] P. P. Galuzio, E. H. de Vasconcelos Segundo, L. dos Santos Coelho, and V. C. Mariani, “Mobopt—multi-objective bayesian optimization,” SoftwareX, vol. 12, p. 100520, 2020.
[180] P. Mercati, B. Li, M. Ergin, C. Tai, M. Kishinevsky, B. Serafimov, S. Ravisundar, E. Walsh, and T. Long, “Mobo-nfv: Automated tuning of a network function virtualization system using multi-objective bayesian optimization,” in 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), pp. 90–98, Bordeaux, France, May 17–21, 2021.
[181] L. Liao, V. Leung, Z. Li, and H.-C. Chao, “Genetic algorithms with variant particle swarm optimization based mutation for generic controller placement in software-defined networks,” Symmetry, vol. 13, no. 7, p. 1133, 2021.
[182] A. S. Da Silva, C. C. Machado, R. V. Bisol, L. Z. Granville, and A. Schaeffer-Filho, “Identification and selection of flow features for accurate traffic classification in sdn,” in 2015 IEEE 14th International Symposium on Network Computing and Applications, pp. 134–141, Cambridge, MA, USA, September 28–30, 2015.
[183] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: Nsga-ii,” IEEE transactions on evolutionary computation, vol. 6, no. 2, pp. 182–197, 2002.
[184] M. Pelikan, D. E. Goldberg, E. Cant´u-Paz, et al., “Boa: The bayesian optimization algorithm,” in Proceedings of the genetic and evolutionary computation conference GECCO-99, vol. 1, pp. 525–532, Orlando, Florida, USA, July 13–17, 1999.
[185] B. Shahriari, K. Swersky, Z. Wang, R. P. Adams, and N. De Freitas, “Taking the human out of the loop: A review of bayesian optimization,” Proceedings of the IEEE, vol. 104, no. 1, pp. 148–175, 2015.
[186] L. Kotthoff, H. Wahab, and P. Johnson, “Bayesian optimization in materials science: A survey,” arXiv preprint arXiv:2108.00002, 2021.
[187] J. Snoek, H. Larochelle, and R. P. Adams, “Practical bayesian optimization of machine learning algorithms,” Advances in neural information processing systems, vol. 25, 2012.
[188] M. Malu, G. Dasarathy, and A. Spanias, “Bayesian optimization in high-dimensional spaces: A brief survey,” in 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA), pp. 1–8, Chania Crete, Greece, July 12–14, 2021.
[189] Z. Zhong, M. Ghobadi, M. Balandat, S. Katti, A. Kazerouni, J. Leach, M. McKillop, and Y. Zhang, “Bow: First real-world demonstration of a bayesian optimization system for wavelength reconfiguration,” in Optical Fiber Communication Conference, pp. F3B–1, Washington, DC, USA, July 26–29, 2021.
[190] C. E. Rasmussen, “Gaussian processes in machine learning,” in Summer school on machine learning, Springer, pp. 63–71, Canberra, Australia, February 2–14, 2003.
[191] A. Gonz´alez-Vidal, P. Rathore, A. S. Rao, J. Mendoza-Bernal, M. Palaniswami, and A. F. Skarmeta-G´omez, “Missing data imputation with bayesian maximum entropy for internet of things applications,” IEEE Internet of Things Journal, 2020.
[192] X. Ning, X. Wang, S. Xu, W. Cai, L. Zhang, L. Yu, and W. Li, “A review of research on co-training,” Concurrency and computation: practice and experience, p. e6276, 2021.
[193] N. Seddigh, B. Nandy, D. Bennett, Y. Ren, S. Dolgikh, C. Zeidler, J. Knoetze, and N. S. Muthyala, “A framework & system for classification of encrypted network traffic using machine learning,” in 2019 15th International Conference on Network and Service Management (CNSM), pp. 1–5, Halifax, NS, Canada, October 21–25, 2019.
[194] H. He, X. Luo, F. Ma, C. Che, and J. Wang, “Network traffic classification based on ensemble learning and co-training,” Science in China Series F: Information Sciences, vol. 52, no. 2, pp. 338–346, 2009.
[195] Y. Li, “Reinforcement learning applications,” arXiv preprint arXiv:1908.06973, 2019.
[196] W.-X. Liu, J. Cai, Y. Wang, Q. C. Chen, and D. Tang, “Mix-flow scheduling using deep reinforcement learning for software-defined data-center networks,” Internet Technology Letters, vol. 2, no. 3, p. e99, 2019.
[197] J. Zhang, M. Ye, Z. Guo, C.-Y. Yen, and H. J. Chao, “Cfr-rl: Traffic engineering with reinforcement learning in sdn,” IEEE Journal on Selected Areas in Communications, vol. 38, no. 10, pp. 2249–2259, 2020.
[198] M. Alauthman, N. Aslam, M. Al-Kasassbeh, S. Khan, A. Al-Qerem, and K.-K. R. Choo, “An efficient reinforcement learning-based botnet detection approach,” Journal of Network and Computer Applications, vol. 150, p. 102479, 2020.
[199] D. Wu, B. Fang, J. Wang, Q. Liu, and X. Cui, “Evading machine learning botnet detection models via deep reinforcement learning,” in ICC 2019-2019 IEEE International Conference on Communications (ICC), pp. 1–6, Shanghai, China, May 20–24, 2019.
[200] M. Woodward and C. Finn, “Active one-shot learning,” arXiv preprint arXiv:1702.06559, 2017.
[201] J. Janisch, T. Pevn`y, and V. Lis`y, “Classification with costly features using deep reinforcement learning,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3959–3966, Honolulu, Hawaii, USA, January 27–February 1, 2019.
[202] S. Bera, S. Misra, and A. V. Vasilakos, “Software-defined networking for internet of things: A survey,” IEEE Internet of Things Journal, vol. 4, no. 6, pp. 1994–2008, 2017.
[203] M. Lopez-Martin, B. Carro, and A. Sanchez-Esguevillas, “Iot type-of-traffic forecasting method based on gradient boosting neural networks,” Future Generation Computer Systems, vol. 105, pp. 331–345, 2020.
[204] H. Li, K. Ota, and M. Dong, “Ls-sdv: Virtual network management in large-scale software-defined iot,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 8, pp. 1783–1793, 2019.
[205] B. K. Saha, L. Haab, and Ł. Podleski, “Safar: Simulated annealing-based flow allocation rules for industrial networks,” IEEE Transactions on Network and Service Management, 2020.
[206] B. Xiang, J. Elias, F. Martignon, and E. Di Nitto, “Resource calendaring for mobile edge computing: Centralized and decentralized optimization approaches,” Computer Networks, vol. 199, p. 108426, 2021.
[207] H. Xing, J. Zhu, R. Qu, P. Dai, S. Luo, and M. A. Iqbal, “An aco for energy-efficient and traffic-aware virtual machine placement in cloud computing,” Swarm and Evolutionary Computation, p. 101012, 2021.
[208] A. Mohamed, M. Hamdan, S. Khan, A. Abdelaziz, S. F. Babiker, M. Imran, and M. Marsono, “Software-defined networks for resource allocation in cloud computing: A survey,” Computer Networks, vol. 195, p. 108151, 2021.
[209] A. Singh, G. S. Aujla, and R. S. Bali, “Intent-based network for data dissemination in software-defined vehicular edge computing,” IEEE Transactions on Intelligent Transportation Systems, 2020.
[210] S. Kaur, K. Kumar, and N. Aggarwal, “A review on p4-programmable data planes: Architecture, research efforts, and future directions,” Computer Communications, vol. 170, pp. 109–129, 2021.
[211] J. Sonchack, A. J. Aviv, E. Keller, and J. M. Smith, “Turboflow: Information rich flow record generation on commodity switches,” in Proceedings of the Thirteenth EuroSys Conference, pp. 1–16, Porto, Portugal, April 23–26, 2018.
[212] M. V. B. da Silva, J. A. Marques, L. P. Gaspary, and L. Z. Granville, “Identifying elephant flows using dynamic thresholds in programmable ixp networks,” Journal of Internet Services and Applications, vol. 11, no. 1, pp. 1–12, 2020.