Distributed Task Management in Fog Computing: A Socially Concave Bandit Game
Xiaotong Cheng, Setareh Maghsudi

TL;DR
This paper introduces a novel game-theoretic framework for distributed task allocation in fog computing, employing bandit feedback and no-regret learning strategies to achieve efficient and adaptive resource management.
Contribution
It formulates the task allocation as a social-concave game with bandit feedback and develops two new no-regret online decision-making algorithms with proven regret bounds.
Findings
Proposed strategies outperform existing methods in simulations.
Theoretical analysis confirms convergence to Nash equilibrium.
Strategies adapt effectively to system heterogeneity and uncertainties.
Abstract
Fog computing leverages the task offloading capabilities at the network's edge to improve efficiency and enable swift responses to application demands. However, the design of task allocation strategies in a fog computing network is still challenging because of the heterogeneity of fog nodes and uncertainties in system dynamics. We formulate the distributed task allocation problem as a social-concave game with bandit feedback and show that the game has a unique Nash equilibrium, which is implementable using no-regret learning strategies (regret with sublinear growth). We then develop two no-regret online decision-making strategies. One strategy, namely bandit gradient ascent with momentum, is an online convex optimization algorithm with bandit feedback. The other strategy, Lipschitz bandit with initialization, is an EXP3 multi-armed bandit algorithm. We establish regret bounds for both…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Age of Information Optimization · IoT and Edge/Fog Computing
