Reproduce “Distributed Linear Bandits for Freshness-Aware Preprocessing in MEC-Enabled Digital Twin Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mariam Yahya, Setareh Maghsudi
The authors develop a method for allocating CPU capacity at multi-access edge computing (MEC) servers among task classes while meeting digital-twin freshness requirements. The digital twin filters out infeasible allocations, then MEC servers learn among the remaining allocations from workload feedback. In simulations, normalized execution-time loss is 0.7774, matching the oracle and beating equal allocation’s 0.9627; this does not measure end-to-end delay.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.