DeF-DReL: Systematic Deployment of Serverless Functions in Fog and Cloud environments using Deep Reinforcement Learning
Chinmaya Kumar Dehury, Shivananda Poojara, Satish Narayana Srirama
TL;DR
This paper tackles the challenge of deploying serverless applications across fog and cloud environments to maximize the number of users served while preserving QoS. It introduces DeF-DReL, a deep reinforcement learning framework that jointly considers user distance/latency, SSR priority, resource constraints, and function characteristics to decide fog versus cloud hosting for each serverless function. The approach formulates a detailed multi-parameter problem, derives an objective of minimizing combined SSR communication and computation latency under realistic resource and size constraints, and implements a DRL-based deployment agent with defined state, action, and reward structures. Empirical results show DeF-DReL significantly reduces fog usage (10–30% of functions on fog) while maintaining service quality, compared with auction/game-theoretic baselines (COG and CORA), highlighting its practical potential for scalable edge-cloud serverless deployments.
Abstract
Fog computing is introduced by shifting cloud resources towards the users' proximity to mitigate the limitations possessed by cloud computing. Fog environment made its limited resource available to a large number of users to deploy their serverless applications, composed of several serverless functions. One of the primary intentions behind introducing the fog environment is to fulfil the demand of latency and location-sensitive serverless applications through its limited resources. The recent research mainly focuses on assigning maximum resources to such applications from the fog node and not taking full advantage of the cloud environment. This introduces a negative impact in providing the resources to a maximum number of connected users. To address this issue, in this paper, we investigated the optimum percentage of a user's request that should be fulfilled by fog and cloud. As a result, we proposed DeF-DReL, a Systematic Deployment of Serverless Functions in Fog and Cloud environments using Deep Reinforcement Learning, using several real-life parameters, such as distance and latency of the users from nearby fog node, user's priority, the priority of the serverless applications and their resource demand, etc. The performance of the DeF-DReL algorithm is further compared with recent related algorithms. From the simulation and comparison results, its superiority over other algorithms and its applicability to the real-life scenario can be clearly observed.