Research on Multi-Objective Task Scheduling Optimization and Reinforcement Learning Decision-Making Methods for Edge-Cloud Collaborative Scalable Information Systems
DOI:
https://doi.org/10.4108/eetsis.14518Keywords:
edge-cloud collaboration, multi-objective scheduling, discrete-event simulation, double DQN, statistical audit, reproducibility, throughput consistencyAbstract
INTRODUCTION: Edge-cloud schedulers must coordinate latency, energy, load balance, and deadline compliance under changing demand while keeping task-arrival and throughput units physically consistent.
OBJECTIVE: This study evaluates MORL-ECSO under an auditable, paired-seed simulation protocol and compares it with tuned heuristic, metaheuristic, value-based, actor-critic, and entropy-regularized baselines.
METHODS: A custom Python discrete-event simulator processes individual tasks in 0.1-s event windows. Offered load is 500-2000 tasks/s, with 4-20 edge nodes and four cloud nodes. DQN, A2C, discrete SAC, and MORL-ECSO receive the same 12,000 training transitions; GA and PSO use a population of 40, 30 iterations, and a common objective. Each reported test point uses 30 independent workload seeds after a 10-s warm-up and a 60-s measurement window. Means, standard deviations, 95% confidence intervals, paired Wilcoxon tests, Holm correction, and rank-biserial effects are reported.
RESULTS: At 2000 tasks/s, MORL-ECSO produced 103.16 ms mean latency, 88.80 kJ energy over 60 s, 94.18% on-time success, and 1947.56 tasks/s throughput. Relative to validation-tuned GA, latency was 18.53% lower, and success was 0.89 percentage points higher.
CONCLUSION: Compared to the optimal baseline, MORL-ECSO improves latency and deadline success rate under high loads without significantly altering energy consumption or throughput. In low-capacity scenarios with four nodes, the genetic algorithm remains superior.
References
[1] Avan A, Azim A, Mahmoud QH. A State-of-the-Art Review of Task Scheduling for Edge Computing: A Delay-Sensitive Application Perspective. Electronics. 2023;12(12):2599. https://doi.org/10.3390/electronics12122599
[2] Patsias V, Amanatidis P, Karampatzakis D, Lagkas T, Michalakopoulou K, Nikitas A. Task Allocation Methods and Optimization Techniques in Edge Computing: A Systematic Review of the Literature. Future Internet. 2023;15(8):254. https://doi.org/10.3390/fi15080254
[3] Peng P, Lin W, Wu W, Zhang H, Peng S, Wu Q, Li K. A survey on computation offloading in edge systems: From the perspective of deep reinforcement learning approaches. Computer Science Review. 2024;53:100656. https://doi.org/10.1016/j.cosrev.2024.100656
[4] Hosseinzadeh M, Azhir E, Lansky J, Mildeova S, Ahmed OH, Malik MH, Khan F. Task Scheduling Mechanisms for Fog Computing: A Systematic Survey. IEEE Access. 2023;11:50994-51017. https://doi.org/10.1109/ACCESS.2023.3277826
[5] Fan W, Zhao L, Liu X, Su Y, Li S, Wu F, Liu Y. Collaborative Service Placement, Task Scheduling, and Resource Allocation for Task Offloading With Edge-Cloud Cooperation. IEEE Transactions on Mobile Computing. 2024;23(1):238-256. https://doi.org/10.1109/TMC.2022.3219261
[6] Fan W, Liu X, Yuan H, Li N, Liu Y. Time-Slotted Task Offloading and Resource Allocation for Cloud-Edge-End Cooperative Computing Networks. IEEE Transactions on Mobile Computing. 2024;23(8):8225-8241. https://doi.org/10.1109/TMC.2024.3349551
[7] Zhang J, Ning Z, Ali RH, Waqas M, Tu S, Ahmad I. A Many-Objective Ensemble Optimization Algorithm for the Edge Cloud Resource Scheduling Problem. IEEE Transactions on Mobile Computing. 2024;23(2):1330-1346. https://doi.org/10.1109/TMC.2023.3235064
[8] Zhang J, Ning Z, Waqas M, Alasmary H, Tu S, Chen S. Hybrid Edge-Cloud Collaborator Resource Scheduling Approach Based on Deep Reinforcement Learning and Multiobjective Optimization. IEEE Transactions on Computers. 2024;73(1):192-205. https://doi.org/10.1109/TC.2023.3326977
[9] Shukla P, Pandey S. MOTORS: multi-objective task offloading and resource scheduling algorithm for heterogeneous fog-cloud computing scenario. The Journal of Supercomputing. 2024;80(15):22315-22361. https://doi.org/10.1007/s11227-024-06315-2
[10] Hosny KM, Awad AI, Khashaba MM, Mohamed ER. New Improved Multi-Objective Gorilla Troops Algorithm for Dependent Tasks Offloading problem in Multi-Access Edge Computing. Journal of Grid Computing. 2023;21(2):21. https://doi.org/10.1007/s10723-023-09656-z
[11] Yin L, Sun J, Zhou J, Gu Z, Li K. ECFA: An Efficient Convergent Firefly Algorithm for Solving Task Scheduling Problems in Cloud-Edge Computing. IEEE Transactions on Services Computing. 2023;16(5):3280-3293. https://doi.org/10.1109/TSC.2023.3293048
[12] Shen W, Lin W, Wu W, Wu H, Li K. Reinforcement learning-based task scheduling for heterogeneous computing in end-edge-cloud environment. Cluster Computing. 2025;28(3):179. https://doi.org/10.1007/s10586-024-04828-2
[13] Ramezani Shahidani F, Ghasemi A, Toroghi Haghighat A, Keshavarzi A. Task scheduling in edge-fog-cloud architecture: a multi-objective load balancing approach using reinforcement learning algorithm. Computing. 2023;105(6):1337-1359. https://doi.org/10.1007/s00607-022-01147-5
[14] Song F, Xing H, Wang X, Luo S, Dai P, Li K. Offloading dependent tasks in multi-access edge computing: A multi-objective reinforcement learning approach. Future Generation Computer Systems. 2022;128:333-348. https://doi.org/10.1016/j.future.2021.10.013
[15] Sellami B, Hakiri A, Ben Yahia S, Berthou P. Energy-aware task scheduling and offloading using deep reinforcement learning in SDN-enabled IoT network. Computer Networks. 2022;210:108957. https://doi.org/10.1016/j.comnet.2022.108957
[16] Yang W, Liu Z, Liu X, Ma Y. Deep reinforcement learning-based low-latency task offloading for mobile-edge computing networks. Applied Soft Computing. 2024;166:112164. https://doi.org/10.1016/j.asoc.2024.112164
[17] Liu J, Mi Y, Zhang X, Li X. Task graph offloading via deep reinforcement learning in mobile edge computing. Future Generation Computer Systems. 2024;158:545-555. https://doi.org/10.1016/j.future.2024.04.034
[18] Pang S, Wang T, Gui H, He X, Hou L. An intelligent task offloading method based on multi-agent deep reinforcement learning in ultra-dense heterogeneous network with mobile edge computing. Computer Networks. 2024;250:110555. https://doi.org/10.1016/j.comnet.2024.110555
[19] Xiong J, Guo P, Wang Y, Meng X, Zhang J, Qian L, Yu Z. Multi-agent deep reinforcement learning for task offloading in group distributed manufacturing systems. Engineering Applications of Artificial Intelligence. 2023;118:105710. https://doi.org/10.1016/j.engappai.2022.105710
[20] Zhou X, Liang W, Yan K, Li W, Wang KIK, Ma J, Jin Q. Edge-Enabled Two-Stage Scheduling Based on Deep Reinforcement Learning for Internet of Everything. IEEE Internet of Things Journal. 2023;10(4):3295-3304. https://doi.org/10.1109/JIOT.2022.3179231
[21] Ibrahim MA, Askar S. An Intelligent Scheduling Strategy in Fog Computing System Based on Multi-Objective Deep Reinforcement Learning Algorithm. IEEE Access. 2023;11:133607-133622. https://doi.org/10.1109/ACCESS.2023.3337034
[22] Wu H, Shen W, Lin W, Li W, Li K. End-Edge-Cloud Heterogeneous Resources Scheduling Method Based on RNN and Particle Swarm Optimization. IEEE Transactions on Network and Service Management. 2025;22(2):1664-1676. https://doi.org/10.1109/TNSM.2024.3507017
[23] Zhang Y, Tang B, Luo J, Zhang J. Deadline-Aware Dynamic Task Scheduling in Edge-Cloud Collaborative Computing. Electronics. 2022;11(15):2464. https://doi.org/10.3390/electronics11152464
[24] Azizi S, Shojafar M, Abawajy J, Buyya R. Deadline-aware and energy-efficient IoT task scheduling in fog computing systems: A semi-greedy approach. Journal of Network and Computer Applications. 2022;201:103333. https://doi.org/10.1016/j.jnca.2022.103333
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Lina Guo, Chengyu Sun
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
