Energy aware Multi Agent Deep Queue Optimization for efficient Resource Allocation and Task Offloading in Cloud Edge
Keywords:
Edge Computing, task offloading, multi agent queue, Intrinsic mode functions, Empirical mode decomposition, XGBoostAbstract
IoT devices finds its application in almost all the fields leading to streaming of enormous amount of big and small data. This leads to many operational problems in load balancing, energy management, latency in processing and storage methods. Edge and cloud computing is leveraged as a potential solution to resolve these problems through its resourceful architectures and on demand services. However, achieving optimal energy efficiency and latency in time critical medical applications is still an open-ended research topic, that draws the attention of the researchers. This work proposes Energy aware Multi Agent Deep Queue Optimisation (E-MADQ) technique that classifies the priorities of the medical tasks using Ensemble Empirical Mode Decomposition (EEMD) smoothened with Extreme Gradient Boost (XGBoost) by extracting Intrinsic Mode Functions and averaging their spectrum characteristics. The offloading decision is made using the multi-agent deep queue optimization where the rewards are calculated based on the energy level of the IoT devices, which is very crucial parameter. By this, the tasks that demands high attention will not be left in starvation and proper resources allocation is done for time critical tasks. The experimental simulation of the proposed methodology shows that a good improvement in service parameters such as mean delivery time, communication and computing delay, execution time and energy level can be attained. In future, the classification of task priorities can be done with powerful deep learning techniques with more focus on dynamism.
Downloads
References
Song, Z., Liu, Y. and Sun, X., 2020. Joint task offloading and resource allocation for NOMA-enabled multi-access mobile edge computing. IEEE Transactions on Communications, 69(3), pp.1548-1564.
Kumaran, K., Sasikala, E. (2023). An efficient task offloading and resource allocation using dynamic arithmetic optimized double deep Q-network in cloud edge platform. Peer-to-Peer Networking and Applications, 16(2), 958-979.
Lin, Z., Lin, M., De Cola, T., Wang, J.B., Zhu, W.P. and Cheng, J., 2021. Supporting IoT with rate-splitting multiple access in satellite and aerial-integrated networks. IEEE Internet of Things Journal, 8(14), pp.11123-11134.
Chen, Y., Liu, Z., Zhang, Y., Wu, Y., Chen, X. and Zhao, L., 2020. Deep reinforcement learning-based dynamic resource management for mobile edge computing in industrial internet of things. IEEE Transactions on Industrial Informatics, 17(7), pp.4925-4934.
Huang, J., Tong, Z. and Feng, Z., 2022. Geographical POI recommendation for Internet of Things: A federated learning approach using matrix factorization. International Journal of Communication Systems, p.e5161.
Lin, H., Zeadally, S., Chen, Z., Labiod, H. and Wang, L., 2020. A survey on computation offloading modeling for edge computing. Journal of Network and Computer Applications, 169, p.102781.
Saranya, G., Sasikala, E. (2023). An efficient computational offloading framework using HAA optimization-based deep reinforcement learning in edge-based cloud computing architecture. Knowledge and Information Systems, 65(1), 409-433..
Li, M., Cheng, N., Gao, J., Wang, Y., Zhao, L. and Shen, X., 2020. Energy-efficient UAV-assisted mobile edge computing: Resource allocation and trajectory optimization. IEEE Transactions on Vehicular Technology, 69(3), pp.3424-3438.
Qi, L., Hu, C., Zhang, X., Khosravi, M.R., Sharma, S., Pang, S. and Wang, T., 2020. Privacy-aware data fusion and prediction with spatial-temporal context for smart city industrial environment. IEEE Transactions on Industrial Informatics, 17(6), pp.4159-4167.
Asim, M., Abd El-Latif, A.A., ELAffendi, M. and Mashwani, W.K., 2022. Energy consumption and sustainable services in intelligent reflecting surface and unmanned aerial vehicles-assisted MEC system for large-scale Internet of Things devices. IEEE Transactions on Green Communications and Networking, 6(3), pp.1396-1407.
Wang, J., Pan, J., Esposito, F., Calyam, P., Yang, Z. and Mohapatra, P., 2019. Edge cloud offloading algorithms: Issues, methods, and perspectives. ACM Computing Surveys (CSUR), 52(1), pp.1-23.
Sharanya, S., Venkataraman, R. and Murali, G., 2022. Predicting remaining useful life of turbofan engines using degradation signal based echo state network. International Journal of Turbo & Jet-Engines.
Feng, C., Han, P., Zhang, X., Yang, B., Liu, Y. and Guo, L., 2022. Computation offloading in mobile edge computing networks: A survey. Journal of Network and Computer Applications, p.103366.
Mao, Y., Zhang, J. and Letaief, K.B., 2016. Dynamic computation offloading for mobile-edge computing with energy harvesting devices. IEEE Journal on Selected Areas in Communications, 34(12), pp.3590-3605.
Dinh, T.Q., La, Q.D., Quek, T.Q. and Shin, H., 2018. Learning for computation offloading in mobile edge computing. IEEE Transactions on Communications, 66(12), pp.6353-6367.
Zhang, K., Mao, Y., Leng, S., Zhao, Q., Li, L., Peng, X., Pan, L., Maharjan, S. and Zhang, Y., 2016. Energy-efficient offloading for mobile edge computing in 5G heterogeneous networks. IEEE access, 4, pp.5896-5907.
Kumaran, K., Sasikala, E. (2023, March). Deep Reinforcement Learning algorithms for Low Latency Edge Computing Systems. In 2023 3rd International conference on Artificial Intelligence and Signal Processing (AISP) (pp. 1-5). IEEE.
Maray, M. and Shuja, J., 2022. Computation offloading in mobile cloud computing and mobile edge computing: survey, taxonomy, and open issues. Mobile Information Systems, 2022.
Alam, M.G.R., Hassan, M.M., Uddin, M.Z., Almogren, A. and Fortino, G., 2019. Autonomic computation offloading in mobile edge for IoT applications. Future Generation Computer Systems, 90, pp.149-157.
Chen, M., Wang, T., Zhang, S. and Liu, A., 2021. Deep reinforcement learning for computation offloading in mobile edge computing environment. Computer Communications, 175, pp.1-12.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.