Edge Microservice Deployment Based on Genetic Algorithm and Hierarchical Fault Tolerance

Abstract

Efficient and stable microservice deployment in edge environments remains challenging due to stringent resource constraints and high node failure rates. Existing works typically address isolated optimization factors, while this singular focus results in suboptimal deployment performance. To overcome these limitations, we propose a new deployment approach combining genetic algorithm (GA) with a hierarchical fault-tolerance mechanism. Our approach first formulates microservice deployment problem as a hierarchical optimization problem, sequentially optimizing response time, cost, deployment success rate under constraints of budget and load. Next, we design a genetic algorithm with an elite chromosome generation strategy to reduce search complexity, incorporating a fault-aware mechanism to avoid unreliable nodes. Furthermore, we introduce a three-layer fault-tolerance mechanism based on cloud-edge-end architecture that performs fault prevention at the cloud layer, real-time remediation at the edge layer, and quality evaluation at the end layer. Extensive experiments on real-world data demonstrate that our approach outperforms baseline methods, improving Quality of Service (QoS) by 13.2% and increasing the deployment success rate (DSR) by 22.9%.