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

2025-01-22

AI Summary

This work addresses the online serverless function scheduling problem under strict budget constraints in edge wireless networks. We propose a lightweight, real-time resource scheduling framework that jointly optimizes cost controllability and latency sensitivity. To the best of our knowledge, this is the first study to integrate deep reinforcement learning (DRL) into serverless edge scheduling with hard budget constraints. We design two online algorithms achieving near-optimal performance—only 1.03× the optimal solution obtained by integer linear programming (ILP)—while enabling millisecond-scale decision-making. Experimental results demonstrate a mere 3% cost deviation from the ILP optimum and reduce decision latency by five orders of magnitude compared to the ILP solver MIDACO. The approach significantly enhances budget predictability and deployment responsiveness, establishing an efficient, scalable, and budget-aware scheduling paradigm for edge-native serverless platforms.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Resource Scheduling
• Budget Constraint
• Edge Computing

Innovation

• Deep Reinforcement Learning
• Serverless Edge Computing
• Optimized Resource Scheduling