Learning Augmented Index Policy for Optimal Service Placement at the Network Edge

TL;DR

This paper develops learning-augmented algorithms for optimal service placement at the network edge, leveraging Whittle indices and addressing unknown, time-varying request rates to minimize latency.

Contribution

It derives explicit Whittle indices for single-service MDPs and introduces two novel algorithms, UCB-Whittle and Q-learning-Whittle, with theoretical performance guarantees.

Findings

Algorithms achieve low regret in learning request rates.

Proposed policies outperform baseline methods in simulations.

The approach effectively balances exploration and exploitation.

Abstract

We consider the problem of service placement at the network edge, in which a decision maker has to choose between $N$ services to host at the edge to satisfy the demands of customers. Our goal is to design adaptive algorithms to minimize the average service delivery latency for customers. We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service. However, solving this $N$-services MDP is computationally expensive due to the curse of dimensionality. To overcome this challenge, we show that the optimal policy for a single-service MDP has an appealing threshold structure, and derive explicitly the Whittle indices for each service as a function of the number of requests from customers based on the theory of Whittle index policy. Since request arrival and service delivery rates are usually unknown and possibly time-varying, we then develop efficient learning augmented algorithms that fully utilize the structure of optimal policies with a low learning regret. The first of these is UCB-Whittle, and relies upon the principle of optimism in the face of uncertainty. The second algorithm, Q-learning-Whittle, utilizes Q-learning iterations for each service by using a two time scale stochastic approximation. We characterize the non-asymptotic performance of UCB-Whittle by analyzing its learning regret, and also analyze the convergence properties of Q-learning-Whittle. Simulation results show that the proposed policies yield excellent empirical performance.