The problem
Papers on edge task offloading each use their own simulator and settings, so results cannot be compared. Existing tools (EdgeCloudSim, iFogSim) are Java-based and hard to connect to modern reinforcement-learning libraries.
Who needs it
Telecom vendors and operators evaluate offloading and resource policies before deploying them in 5G edge sites.
Idea of the approach
- Design a Python simulator: users, base stations, edge servers, cloud; tasks with size, deadline and security level.
- Expose it as a Gym/Gymnasium environment so RL agents can be trained directly.
- Implement classic baselines (local, random, greedy, HEFT-like) and one DRL policy.
- Publish scenarios and results as a benchmark (GitHub + documentation).
What you will build and deliver
- The open-source simulator with documentation and tests.
- Benchmark scenarios and baseline results.
- A paper (tool/benchmark track).
Skills needed
Python, object-oriented design, basic networking; RL can be learned during the project.
Research contribution & where to publish
Contribution: a reproducible benchmark for MEC offloading linked to the survey of ML resource allocation. Venues: IEEE INFOCOM workshops, SIMUtools, SoftwareX, Simulation Modelling Practice and Theory.
Key references — start reading here
- Y. Mao, C. You, J. Zhang, K. Huang, K. B. Letaief. A Survey on Mobile Edge Computing: The Communication Perspective. IEEE Communications Surveys & Tutorials, 2017.
- C. Sonmez, A. Ozgovde, C. Ersoy. EdgeCloudSim: An environment for performance evaluation of edge computing systems. Transactions on Emerging Telecommunications Technologies, 2018.
- R. N. Calheiros, R. Ranjan, A. Beloglazov, C. A. F. De Rose, R. Buyya. CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and Experience, 2011.
- H. Djigal, J. Xu, L. Liu, Y. Zhang. Machine and Deep Learning for Resource Allocation in Multi-Access Edge Computing: A Survey. IEEE Communications Surveys & Tutorials, 2022.
Interested?
Send the topic title and the courses you have taken.
Contact Dr. Hamza DjigalOther topics in Edge and cloud scheduling
Budget- and deadline-aware autoscaling of Kubernetes microservices with reinforcement learning
Carbon-aware scheduling of data-pipeline workflows across cloud regions
Spot-instance-aware workflow scheduling to cut cloud costs for data pipelines
Predicting serverless cold starts and pre-warming functions with machine learning