Dynamic System Reconfiguration in Stable and Green Edge Service Provisioning
Mobile Networks and Applications - Trang 1-17
Tóm tắt
Multi-access Edge Computing (MEC) has emerged as an essential paradigm to address the challenges posed by the proliferation of connected mobile devices. By constructing a MEC-based service system with edge servers in proximity and deploying modules or services on them, these devices can perform complex tasks efficiently with their own resources. However, the significant energy consumption associated with this computing paradigm poses a major obstacle to its widespread adoption. Thus, it is imperative to carefully configure the MEC-based service system to ensure optimal performance and cost-effectiveness. Furthermore, the dynamic nature of the system’s environment or context necessitates that the configuration be adaptable over time to fully utilize limited resources and ensure stability and energy efficiency. In this paper, we present an investigation and model of how mobile devices’ service requests are processed in a MEC-based service system. We propose a reinforcement learning-based algorithm to train a policy that dynamically reconfigures the system to minimize the average service response time while maximizing stability and energy efficiency. Our approach is validated through experiments on the YouTube usage dataset, and we demonstrate that it outperforms the baseline models.
Tài liệu tham khảo
Xiang, Z., Deng, S., Zheng, Y., Wang, D., Tehari, J., Zheng, Z.: Energy-effective iot services in balanced edge-cloud collaboration systems. In: 2021 IEEE International Conference on Web Services (ICWS), pp. 219–229 (2021). IEEE
Xiang, Z., Deng, S., Jiang, F., Gao, H., Tehari, J., Yin, J.: Computing power allocation and traffic scheduling for edge service provisioning. In: 2020 IEEE International Conference on Web Services (ICWS), pp. 394–403 (2020). IEEE
citation_journal_title=IEEE internet of things journal; citation_title=Edge computing: Vision and challenges; citation_author=W Shi, J Cao, Q Zhang, Y Li, L Xu; citation_volume=3; citation_issue=5; citation_publication_date=2016; citation_pages=637-646; citation_doi=10.1109/JIOT.2016.2579198; citation_id=CR3
citation_journal_title=IEEE Journal on Selected Areas in Communications; citation_title=Dynamic computation offloading for mobile-edge computing with energy harvesting devices; citation_author=Y Mao, J Zhang, KB Letaief; citation_volume=34; citation_issue=12; citation_publication_date=2016; citation_pages=3590-3605; citation_doi=10.1109/JSAC.2016.2611964; citation_id=CR4
citation_journal_title=IEEE Transactions on Mobile Computing; citation_title=Multi-objective computation sharing in energy and delay constrained mobile edge computing environments; citation_author=A Bozorgchenani, F Mashhadi, D Tarchi, SS Monroy; citation_volume=20; citation_issue=10; citation_publication_date=2021; citation_pages=2992-3005; citation_doi=10.1109/TMC.2020.2994232; citation_id=CR5
Mavromoustakis, C.X., Mastorakis, G., Batalla, J.M., Rodrigues, J.J., Sahalos, J.N.: Edge computing for offload-aware energy conservation using m2m recommendation mechanisms. In: 2019 IEEE Global Communications Conference (GLOBECOM), pp. 1–6 (2019). IEEE
citation_journal_title=IEEE Transactions on Industrial Informatics; citation_title=Exploring placement of heterogeneous edge servers for response time minimization in mobile edge-cloud computing; citation_author=K Cao, L Li, Y Cui, T Wei, S Hu; citation_volume=17; citation_issue=1; citation_publication_date=2020; citation_pages=494-503; citation_doi=10.1109/TII.2020.2975897; citation_id=CR7
citation_journal_title=Peer-to-Peer Networking and Applications; citation_title=Energy-effective artificial internet-of-things application deployment in edge-cloud systems; citation_author=Z Xiang, Y Zheng, M He, L Shi, D Wang, S Deng, Z Zheng; citation_volume=15; citation_issue=2; citation_publication_date=2022; citation_pages=1029-1044; citation_doi=10.1007/s12083-021-01273-5; citation_id=CR8
citation_journal_title=Ad Hoc Networks; citation_title=Joint service placement and request routing in mobile edge computing; citation_author=B Yuan, S Guo, Q Wang; citation_volume=120; citation_publication_date=2021; citation_doi=10.1016/j.adhoc.2021.102543; citation_id=CR9
citation_journal_title=IEEE Transactions on Services Computing; citation_title=A cyclic game for service-oriented resource allocation in edge computing; citation_author=S Ma, S Guo, K Wang, W Jia, M Guo; citation_volume=13; citation_issue=4; citation_publication_date=2020; citation_pages=723-734; citation_doi=10.1109/TSC.2020.2966196; citation_id=CR10
citation_journal_title=IEEE Transactions on Parallel and Distributed Systems; citation_title=On the effective parallelization and near-optimal deployment of service function chains; citation_author=J Luo, J Li, L Jiao, J Cai; citation_volume=32; citation_issue=5; citation_publication_date=2020; citation_pages=1238-1255; citation_doi=10.1109/TPDS.2020.3043768; citation_id=CR11
citation_journal_title=IEEE Transactions on Services Computing; citation_title=Heterogeneous computational resource allocation for noma: Toward green mobile edge-computing systems; citation_author=A Mohajer, MS Daliri, A Mirzaei, A Ziaeddini, M Nabipour, M Bavaghar; citation_volume=16; citation_issue=2; citation_publication_date=2022; citation_pages=1225-1238; citation_doi=10.1109/TSC.2022.3186099; citation_id=CR12
citation_journal_title=IEEE Transactions on Services Computing; citation_title=Joint optimization of request assignment and computing resource allocation in multi-access edge computing; citation_author=H Liu, X Long, Z Li, S Long, R Ran, H-M Wang; citation_volume=16; citation_issue=2; citation_publication_date=2022; citation_pages=1254-1267; citation_doi=10.1109/TSC.2022.3180105; citation_id=CR13
citation_journal_title=IEEE Internet of Things Journal; citation_title=Online computation offloading and resource scheduling in mobile-edge computing; citation_author=T Liu, Y Zhang, Y Zhu, W Tong, Y Yang; citation_volume=8; citation_issue=8; citation_publication_date=2021; citation_pages=6649-6664; citation_doi=10.1109/JIOT.2021.3051427; citation_id=CR14
citation_journal_title=IEEE Transactions on Parallel and Distributed Systems; citation_title=Distributed and dynamic service placement in pervasive edge computing networks; citation_author=Z Ning, P Dong, X Wang, S Wang, X Hu, S Guo, T Qiu, B Hu, RY Kwok; citation_volume=32; citation_issue=6; citation_publication_date=2020; citation_pages=1277-1292; citation_doi=10.1109/TPDS.2020.3046000; citation_id=CR15
citation_journal_title=Computer Communications; citation_title=A delay-sensitive resource allocation algorithm for container cluster in edge computing environment; citation_author=S Guo, K Zhang, B Gong, W He, X Qiu; citation_volume=170; citation_publication_date=2021; citation_pages=144-150; citation_doi=10.1016/j.comcom.2021.01.020; citation_id=CR16
citation_journal_title=IEEE Transactions on Wireless Communications; citation_title=Lyapunov-guided deep reinforcement learning for stable online computation offloading in mobile-edge computing networks; citation_author=S Bi, L Huang, H Wang, Y-JA Zhang; citation_volume=20; citation_issue=11; citation_publication_date=2021; citation_pages=7519-7537; citation_doi=10.1109/TWC.2021.3085319; citation_id=CR17
citation_journal_title=Future Generation Computer Systems; citation_title=A platform for integrating heterogeneous data and developing smart city applications; citation_author=J Pereira, T Batista, E Cavalcante, A Souza, F Lopes, N Cacho; citation_volume=128; citation_publication_date=2022; citation_pages=552-566; citation_doi=10.1016/j.future.2021.10.030; citation_id=CR18
Dustdar, S., Nastic, S., Scekic, O.: Smart cities - the internet of things, people and systems (2017)
Chen, C., Wei, H., Xu, N., Zheng, G., Yang, M., Xiong, Y., Xu, K., Li, Z.: Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3414–3421 (2020)
citation_journal_title=IEEE wireless communications; citation_title=Container-as-a-service at the edge: Trade-off between energy efficiency and service availability at fog nano data centers; citation_author=K Kaur, T Dhand, N Kumar, S Zeadally; citation_volume=24; citation_issue=3; citation_publication_date=2017; citation_pages=48-56; citation_doi=10.1109/MWC.2017.1600427; citation_id=CR21
citation_journal_title=Journal of Cloud Computing; citation_title=A placement architecture for a container as a service (caas) in a cloud environment; citation_author=MK Hussein, MH Mousa, MA Alqarni; citation_volume=8; citation_issue=1; citation_publication_date=2019; citation_pages=1-15; citation_id=CR22
Takouna, I., Dawoud, W., Meinel, C.: Accurate mutlicore processor power models for power-aware resource management. In: 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing, pp. 419–426 (2011). IEEE
Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv preprint
arXiv:1509.02971
(2015)
Gao, H., Wang, Z., Ji, S.: Large-scale learnable graph convolutional networks. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1416–1424 (2018)
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871 (2019). PMLR
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870 (2018). PMLR
Lee, K., Eoff, B., Caverlee, J.: Seven months with the devils: A long-term study of content polluters on twitter. (2011)
citation_journal_title=Computer Communications; citation_title=Weighted utility aware computational overhead minimization of wireless power mobile edge cloud; citation_author=A Mahmood, A Ahmed, M Naeem, MR Amirzada, A Al-Dweik; citation_volume=190; citation_publication_date=2022; citation_pages=178-189; citation_doi=10.1016/j.comcom.2022.04.017; citation_id=CR29
citation_journal_title=Mobile Networks and Applications; citation_title=Robust and cost-effective resource allocation for complex iot applications in edge-cloud collaboration; citation_author=Z Xiang, Y Zheng, D Wang, M He, C Zhang, Z Zheng; citation_volume=27; citation_issue=4; citation_publication_date=2022; citation_pages=1506-1519; citation_doi=10.1007/s11036-022-01977-9; citation_id=CR30
citation_journal_title=IEEE Transactions on Intelligent Transportation Systems; citation_title=Large-scale many-objective deployment optimization of edge servers; citation_author=B Cao, S Fan, J Zhao, S Tian, Z Zheng, Y Yan, P Yang; citation_volume=22; citation_issue=6; citation_publication_date=2021; citation_pages=3841-3849; citation_doi=10.1109/TITS.2021.3059455; citation_id=CR31
citation_journal_title=IEEE Transactions on Parallel and Distributed Systems; citation_title=An empirical evaluation of performance-memory trade-offs in time warp; citation_author=SR Das, RM Fujimoto; citation_volume=8; citation_issue=2; citation_publication_date=1997; citation_pages=210-224; citation_doi=10.1109/71.577269; citation_id=CR32
Deng, S., Huang, L., Taheri, J., Yin, J., Zhou, M., Zomaya, A.Y.: Mobility-aware service composition in mobile communities. IEEE Trans. Systems, Man, and Cybernetics: Systems 47(3), 555–568 (2017)
Fadlullah, Z.M., Mao, B., Kato, N.: Balancing qos and security in the edge: Existing practices, challenges, and 6g opportunities with machine learning. IEEE Communications Surveys & Tutorials (2022)