A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation

TL;DR

This paper introduces two novel online pricing algorithms based on multi-armed bandit models for efficient, real-time heterogeneous edge resource allocation without prior demand knowledge, improving platform profit and user experience.

Contribution

It develops two new bandit-based online pricing mechanisms, KL-UCB and Min-Max Optimal, tailored for edge resource allocation with no need for demand distribution assumptions.

Findings

Proposed algorithms outperform benchmark bandit schemes in numerical tests.

The mechanisms adapt dynamically to demand, enhancing profit and resource utilization.

Real-time operation without demand prior knowledge is feasible and effective.

Abstract

Edge Computing (EC) offers a superior user experience by positioning cloud resources in close proximity to end users. The challenge of allocating edge resources efficiently while maximizing profit for the EC platform remains a sophisticated problem, especially with the added complexity of the online arrival of resource requests. To address this challenge, we propose to cast the problem as a multi-armed bandit problem and develop two novel online pricing mechanisms, the Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm and the Min-Max Optimal algorithm, for heterogeneous edge resource allocation. These mechanisms operate in real-time and do not require prior knowledge of demand distribution, which can be difficult to obtain in practice. The proposed posted pricing schemes allow users to select and pay for their preferred resources, with the platform dynamically adjusting resource prices based on observed historical data. Numerical results show the advantages of the proposed mechanisms compared to several benchmark schemes derived from traditional bandit algorithms, including the Epsilon-Greedy, basic UCB, and Thompson Sampling algorithms.