Cold-Start Aware Offloading and Resource Allocation by Importance Sampling-Based Double Dueling DQN in Serverless Edge Computing

Serverless edge computing seamlessly integrates edge computing with serverless computing, not only overcoming the limitations of resource-constrained edge nodes but also alleviating the high latency associated with cloud response. Due to the elastic scalability of serverless computing platforms, the cold start of latency-sensitive serverless functions (SFs) has become a significant challenge. Traditional strategies, such as resource reservation and prewarming, often suffer from low resource utilization. Meanwhile, offloading-based approaches simplify the problem by assuming a fixed high cold start delay cost, which is unsuitable for heterogeneous serverless edge computing scenarios. This paper proposes a Cold-Start aware offloading by double-dueling-DQN (CSODQN) model for SFs in a cloud-edge-device serverless computing system. The model creates an instance warming pool for SFs to enable reuse and allocates edge service node resources based on the priority of user and SFs, achieving multi-objective offloading optimization that considers cold starts. Our goal is to balance the frequency of cold start and resource utilization. To address the partially observable offloading optimization problem among agents, we employ a multi-agent deep reinforcement learning approach. By introducing an priority of action based sampling strategy, we accelerate the convergence of learning for each agent. Simulation results demonstrate that our method improves task success rates, reduces average task latency and cold start occurrences, and enhances resource utilization. Our approach alleviates the frequency of cold starts without excessively consuming system resources and costs, achieving long-term optimization of service quality, device energy consumption, and expenses.