Cost Optimization for Serverless Edge Computing with Budget Constraints using Deep Reinforcement Learning

TL;DR

This paper introduces reinforcement learning-based algorithms to optimize serverless function scheduling at the edge under budget constraints, significantly reducing costs and decision time compared to traditional ILP methods.

Contribution

It presents novel online reinforcement learning algorithms for cost-effective serverless edge computing with budget limits, outperforming ILP solutions in efficiency and near-optimality.

Findings

Algorithms approximate ILP solutions within a factor of 1.03

Decision-making time is 100,000 times faster than ILP

Effective handling of diverse serverless functions and heterogeneous devices

Abstract

Serverless computing adopts a pay-as-you-go billing model where applications are executed in stateless and shortlived containers triggered by events, resulting in a reduction of monetary costs and resource utilization. However, existing platforms do not provide an upper bound for the billing model which makes the overall cost unpredictable, precluding many organizations from managing their budgets. Due to the diverse ranges of serverless functions and the heterogeneous capacity of edge devices, it is challenging to receive near-optimal solutions for deployment cost in a polynomial time. In this paper, we investigated the function scheduling problem with a budget constraint for serverless computing in wireless networks. Users and IoT devices are sending requests to edge nodes, improving the latency perceived by users. We propose two online scheduling algorithms based on reinforcement learning, incorporating several important characteristics of serverless functions. Via extensive simulations, we justify the superiority of the proposed algorithm by comparing with an ILP solver (Midaco). Our results indicate that the proposed algorithms efficiently approximate the results of Midaco within a factor of 1.03 while our decision-making time is 5 orders of magnitude less than that of Midaco.