{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T11:44:54Z","timestamp":1743594294074,"version":"3.37.3"},"reference-count":56,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:00:00Z","timestamp":1706832000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2021YFE0111600"]},{"name":"Natural Science Foundation of Shan-dong","award":["ZR2021LZH006"]},{"name":"Taishan Scholars Program"},{"name":"JSPS KAKENHI","award":["JP20H04174","JP22K11989"]},{"name":"Leading Initiative for Excellent Young Researchers (LEADER)"},{"name":"JST, PRESTO","award":["JPMJPR21P3"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"The development of emerging information technologies, such as the Internet of Things (IoT), edge computing, and blockchain, has triggered a significant increase in IoT application services and data volume. Ensuring satisfactory service quality for diverse IoT application services based on limited network resources has become an urgent issue. Generalized processor sharing (GPS), functioning as a central resource scheduling mechanism guiding differentiated services, stands as a key technology for implementing on-demand resource allocation. The performance prediction of GPS is a crucial step that aims to capture the actual allocated resources using various queue metrics. Some methods (mainly analytical methods) have attempted to establish upper and lower bounds or approximate solutions. Recently, artificial intelligence (AI) methods, such as deep learning, have been designed to assess performance under self-similar traffic. However, the proposed methods in the literature have been developed for specific traffic scenarios with predefined constraints, thus limiting their real-world applicability. Furthermore, the absence of a benchmark in the literature leads to an unfair performance prediction comparison. To address the drawbacks in the literature, an AI-enabled performance benchmark with comprehensive traffic-oriented experiments showcasing the performance of existing methods is presented. Specifically, three types of methods are employed: traditional approximate analytical methods, traditional machine learning-based methods, and deep learning-based methods. Following that, various traffic flows with different settings are collected, and intricate experimental analyses at both the feature and method levels under different traffic conditions are conducted. Finally, insights from the experimental analysis that may be beneficial for the future performance prediction of GPS are derived.<\/jats:p>","DOI":"10.3390\/s24030980","type":"journal-article","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T14:42:32Z","timestamp":1706884952000},"page":"980","source":"Crossref","is-referenced-by-count":4,"title":["On-Demand Centralized Resource Allocation for IoT Applications: AI-Enabled Benchmark"],"prefix":"10.3390","volume":"24","author":[{"given":"Ran","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan 250101, China"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan 250101, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2788-3451","authenticated-orcid":false,"given":"Mianxiong","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Information and Electronic Engineering, Muroran Institute of Technology, Muroran 050-8585, Japan"}]},{"given":"Kaoru","family":"Ota","sequence":"additional","affiliation":[{"name":"Department of Information and Electronic Engineering, Muroran Institute of Technology, Muroran 050-8585, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"25114","DOI":"10.1109\/JSEN.2021.3060953","article-title":"Resource Efficient Geo-Textual Hierarchical Clustering Framework for Social IoT Applications","volume":"21","author":"Shuja","year":"2021","journal-title":"IEEE Sensors J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.icte.2022.06.006","article-title":"Towards 6G internet of things: Recent advances, use cases, and open challenges","volume":"9","author":"Qadir","year":"2023","journal-title":"ICT Express"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MNET.2019.1800221","article-title":"Optimal Edge Resource Allocation in IoT-Based Smart Cities","volume":"33","author":"Zhao","year":"2019","journal-title":"IEEE Netw."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2052","DOI":"10.1109\/TII.2019.2951728","article-title":"QoS-guarantee resource allocation for multibeam satellite industrial internet of things with NOMA","volume":"17","author":"Liu","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1109\/COMST.2021.3059896","article-title":"A survey on resource allocation for 5G heterogeneous networks: Current research, future trends, and challenges","volume":"23","author":"Xu","year":"2021","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"ref_6","unstructured":"Li, T., Sanjabi, M., Beirami, A., and Smith, V. (2019). Fair resource allocation in federated learning. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1109\/JSAC.2019.2906746","article-title":"Fairness-Aware Dynamic Rate Control and Flow Scheduling for Network Utility Maximization in Network Service Chain","volume":"37","author":"Gu","year":"2019","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1109\/TNSE.2020.3038783","article-title":"Flow Scheduling of Service Chain Processing in a NFV-Based Network","volume":"8","author":"Chen","year":"2021","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_9","unstructured":"Mannersalo, P., and Norros, I. (2002, January 23\u201327). GPS schedulers and Gaussian traffic. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), New York, NY, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/S1389-1286(02)00302-X","article-title":"A most probable path approach to queueing systems with general Gaussian input","volume":"40","author":"Mannersalo","year":"2002","journal-title":"Comput. Netw."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, R., Liu, L., Lu, X., Yan, Z., and Li, H. (2020, January 17\u201319). Performance Modeling of a General GPS Scheduling Under Long Range Dependent Traffic. Proceedings of the ISPA\/BDCloud\/SocialCom\/SustainCom 2020, Exeter, UK.","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00111"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, R., Liu, N., Liu, L., Zhang, W., Yuan, H., Dong, M., and Cui, L. (2022, January 10\u201316). Is it fair? Resource allocation for differentiated services on demands. Proceedings of the 2022 IEEE International Conference on Web Services (ICWS), Barcelona, Spain.","DOI":"10.1109\/ICWS55610.2022.00059"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: Trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ray, S. (2019, January 14\u201316). A quick review of machine learning algorithms. Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India.","DOI":"10.1109\/COMITCon.2019.8862451"},{"key":"ref_15","unstructured":"Bell, J. (2022). Machine Learning and the City: Applications in Architecture and Urban Design, Wiley."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1049\/cit2.12114","article-title":"Scope of machine learning applications for addressing the challenges in next-generation wireless networks","volume":"7","author":"Samanta","year":"2022","journal-title":"CAAI Trans. Intell. Technol."},{"key":"ref_17","first-page":"581","article-title":"Framework for Sustainable Energy Management using Smart Grid Panels Integrated with Machine Learning and IOT based Approach","volume":"12","author":"Ahmad","year":"2024","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chauhan, N., Choudhary, N., and George, K. (2016, January 14\u201317). A comparison of reinforcement learning based approaches to appliance scheduling. Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics (IC3I), Greater Noida, India.","DOI":"10.1109\/IC3I.2016.7917970"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chinchali, S., Hu, P., Chu, T., Sharma, M., Bansal, M., Misra, R., Pavone, M., and Katti, S. (2018, January 2\u20137). Cellular network traffic scheduling with deep reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11339"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rjoub, G., and Bentahar, J. (2017, January 21\u201323). Cloud task scheduling based on swarm intelligence and machine learning. Proceedings of the 2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud), Prague, Czech Republic.","DOI":"10.1109\/FiCloud.2017.52"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Qiao, M., Ma, Y., Bian, Y., and Liu, J. (2015, January 15\u201318). Real-time multi-application network traffic identification based on machine learning. Proceedings of the Advances in Neural Networks\u2013ISNN 2015: 12th International Symposium on Neural Networks, ISNN 2015, Jeju, Republic of Korea.","DOI":"10.1007\/978-3-319-25393-0_52"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Perera, P., Tian, Y.C., Fidge, C., and Kelly, W. (2017, January 14\u201318). A comparison of supervised machine learning algorithms for classification of communications network traffic. Proceedings of the Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China.","DOI":"10.1007\/978-3-319-70087-8_47"},{"key":"ref_23","first-page":"3897","article-title":"Machine Learning and Deep Learning: A Review of Methods and Applications","volume":"10","author":"Sharifani","year":"2023","journal-title":"World Inf. Technol. Eng. J."},{"key":"ref_24","unstructured":"Vashishth, T.K., Sharma, V., Sharma, K.K., Kumar, B., Chaudhary, S., and Panwar, R. (2024). AI and Blockchain Applications in Industrial Robotics, IGI Global."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103054","DOI":"10.1016\/j.seta.2023.103054","article-title":"Design of deep learning model for radio resource allocation in 5G for massive iot device","volume":"56","author":"Saravanan","year":"2023","journal-title":"Sustain. Energy Technol. Assessments"},{"key":"ref_26","first-page":"100","article-title":"Single-image dehazing based on two-stream convolutional neural network","volume":"2","author":"Meng","year":"2022","journal-title":"J. Artif. Intell. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3281","DOI":"10.1109\/TWC.2019.2912754","article-title":"Deep Reinforcement Learning-Based Modulation and Coding Scheme Selection in Cognitive Heterogeneous Networks","volume":"18","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s11063-018-9804-x","article-title":"A learning-based multimodel integrated framework for dynamic traffic flow forecasting","volume":"49","author":"Zhou","year":"2019","journal-title":"Neural Process. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1109\/JIOT.2023.3293206","article-title":"Data-Driven Resource Allocation for Deep Learning in IoT Networks","volume":"11","author":"Chun","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1007\/s11036-020-01566-8","article-title":"Deep learning based resources allocation for internet-of-things deployment underlaying cellular networks","volume":"25","author":"ElHalawany","year":"2020","journal-title":"Mob. Netw. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1023\/A:1019163509718","article-title":"Large deviations and the generalized processor sharing scheduling for a multiple-queue system","volume":"28","author":"Zhang","year":"1998","journal-title":"Queueing Syst."},{"key":"ref_32","unstructured":"Zhang, Z.L. (1995). Computer Science Department Faculty Publication Series, University of Massachusetts Amherst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1023\/A:1019151423773","article-title":"Large deviations analysis of the generalized processor sharing policy","volume":"32","author":"Bertsimas","year":"1999","journal-title":"Queueing Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1109\/LCOMM.2007.061971","article-title":"Performance modelling of hybrid PQ-GPS systems under long-range dependent network traffic","volume":"11","author":"Jin","year":"2007","journal-title":"IEEE Commun. Lett."},{"key":"ref_35","unstructured":"Ashour, M., and Le-Ngoc, T. (2003, January 1\u20135). Priority queuing of long-range dependent traffic. Proceedings of the GLOBECOM\u201903, IEEE Global Telecommunications Conference (IEEE Cat. No. 03CH37489), San Francisco, CA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1049\/iet-com.2007.0325","article-title":"Multi-scale analysis of generalised processor sharing queues with long-range-dependent traffic inputs and variable service rates","volume":"3","author":"Ashour","year":"2009","journal-title":"IET Commun."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/90.234856","article-title":"A generalized processor sharing approach to flow control in integrated services networks: The single-node case","volume":"1","author":"Parekh","year":"1993","journal-title":"IEEE\/ACM TON"},{"key":"ref_38","unstructured":"Chandrasekaran, B. (2009). Survey of Network Traffic Models, Waschington University."},{"key":"ref_39","unstructured":"Cao, J., Cleveland, W.S., Lin, D., and Sun, D.X. (2003). Nonlinear Estimation and Classification, Springer."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1109\/90.650143","article-title":"Self-similarity in World Wide Web traffic: Evidence and possible causes","volume":"5","author":"Crovella","year":"1997","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_41","unstructured":"Liu, S.G., Wang, P.J., and Qu, L.J. (2005, January 18\u201321). Modeling and simulation of self-similar data traffic. Proceedings of the 2005 International Conference on Machine Learning and Cybernetics, Guangzhou, China."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1214\/aoms\/1177704267","article-title":"The Poisson tendency in traffic distribution","volume":"34","author":"Breiman","year":"1963","journal-title":"Ann. Math. Stat."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/90.392383","article-title":"Wide area traffic: The failure of Poisson modeling","volume":"3","author":"Paxson","year":"1995","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_44","unstructured":"Karagiannis, T., Molle, M., Faloutsos, M., and Broido, A. (2004, January 7\u201311). A nonstationary Poisson view of Internet traffic. Proceedings of the IEEE INFOCOM 2004, Hong Kong, China."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/90.282603","article-title":"On the self-similar nature of Ethernet traffic (extended version)","volume":"2","author":"Leland","year":"1994","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1145\/190809.190339","article-title":"Analysis, Modeling and Generation of Self-Similar VBR Video Traffic","volume":"24","author":"Garrett","year":"1994","journal-title":"ACM SIGCOMM Comput. Commun. Rev."},{"key":"ref_47","first-page":"39","article-title":"Exact asymptotic queue length distribution for fractional brownian traffic","volume":"1","author":"Narayan","year":"1998","journal-title":"Adv. Perform. Anal."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1109\/TNET.2008.925630","article-title":"L\u00c9vy Flights and Fractal Modeling of Internet Traffic","volume":"17","author":"Terdik","year":"2009","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.1109\/TCOMM.2013.050313.112217","article-title":"Modelling and analysis of an integrated scheduling scheme with heterogeneous LRD and SRD traffic","volume":"12","author":"Jin","year":"2013","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Breiman, L.I., Friedman, J.H., Olshen, R.A., and Stone, C.J. (1984). Classification and Regression Trees. Wadsworth. Biometrics, 40.","DOI":"10.2307\/2530946"},{"key":"ref_51","unstructured":"Zemel, R.S., and Pitassi, T. (2000, January 1). A Gradient-Based Boosting Algorithm for Regression Problems. Proceedings of the 13th International Conference on Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1049\/cit2.12031","article-title":"Bloody Mahjong playing strategy based on the integration of deep learning and XGBoost","volume":"7","author":"Gao","year":"2022","journal-title":"CAAI Trans. Intell. Technol."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"\u00c7ayir, A., Yenido\u011fan, I., and Da\u011f, H. (2018, January 20\u201323). Feature Extraction Based on Deep Learning for Some Traditional Machine Learning Methods. Proceedings of the 2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia and Herzegovina.","DOI":"10.1109\/UBMK.2018.8566383"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1017\/S0962492900002919","article-title":"Approximation theory of the MLP model in neural networks","volume":"8","author":"Pinkus","year":"1999","journal-title":"Acta Numer."},{"key":"ref_55","unstructured":"Kipf, T.N., and Welling, M. (2017, January 21\u201326). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA."},{"key":"ref_56","unstructured":"Quan, Z., and Chung, J.M. (2003, January 11\u201315). Priority queueing analysis of self-similar in high-speed networks. Proceedings of the IEEE International Conference on Communications, ICC\u201903, Anchorage, AK, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/3\/980\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T23:56:00Z","timestamp":1737417360000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/3\/980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,2]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["s24030980"],"URL":"https:\/\/doi.org\/10.3390\/s24030980","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2024,2,2]]}}}