Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Chen Chen, Peiyuan Guan, Ziru Chen, Amir Taherkordi, Fen Hou, Lin X. Cai

TL;DR

This work targets budget-constrained scheduling for serverless edge computing, modeling the deployment cost as the sum of function switching, running, and routing costs and enforcing per-function budgets. It proves NP-hardness by reduction from the Generalized Assignment Problem and proposes two online DRL policies, DFaaS (DQN) and PFaaS (PPO), to learn cost-minimizing policies under heterogeneous edge resources. The methods are evaluated on real-world topology and trace data, showing near-optimal performance (within about 1.03–1.06 of an ILP solver) with several orders of magnitude faster decision-making, enabling practical online deployment. The results demonstrate the practical potential of budget-aware DRL for scalable, cost-controlled serverless edge workflows, with implications for budget-bound cloud-edge orchestration and QoS management.

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.

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

TL;DR

This work targets budget-constrained scheduling for serverless edge computing, modeling the deployment cost as the sum of function switching, running, and routing costs and enforcing per-function budgets. It proves NP-hardness by reduction from the Generalized Assignment Problem and proposes two online DRL policies, DFaaS (DQN) and PFaaS (PPO), to learn cost-minimizing policies under heterogeneous edge resources. The methods are evaluated on real-world topology and trace data, showing near-optimal performance (within about 1.03–1.06 of an ILP solver) with several orders of magnitude faster decision-making, enabling practical online deployment. The results demonstrate the practical potential of budget-aware DRL for scalable, cost-controlled serverless edge workflows, with implications for budget-bound cloud-edge orchestration and QoS management.

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.
Paper Structure (23 sections, 12 equations, 4 figures, 1 table)

This paper contains 23 sections, 12 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Model and Problem Formulation
  4. System model
  5. Function switching cost
  6. Function running cost
  7. Traffic routing cost
  8. Problem formulation
  9. NP-hardness
  10. Proposed Deep Reinforcement Learning Solution
  11. Markov Decision Process Formulation
  12. State Space
  13. Action Space
  14. Reward
  15. Algorithm Description
  16. ...and 8 more sections

Figures (4)

  • Figure 1: Edge servers in Melbourne CBD area
  • Figure 2: Box plots of deployment cost
  • Figure 3: Average cost and acceptance rate
  • Figure 4: Decision-making time