Sustainable Graph Analytics Workload Scheduling with Evolutionary Reinforcement Learning in Edge-Cloud Systems

2026-05-13

AI Summary

Graph computing in heterogeneous edge-cloud environments faces significant challenges in balancing service-level agreement (SLA) compliance with sustainability due to high energy consumption and carbon emissions. To address this, this work proposes MERSEM, a novel framework that uniquely integrates multi-objective evolutionary algorithms with deep reinforcement learning to co-optimize graph workload scheduling strategies. By synergistically combining global exploration and local adaptation capabilities, MERSEM dynamically responds to fluctuations in carbon intensity while explicitly modeling resource heterogeneity and workload characteristics. This enables simultaneous SLA assurance and carbon footprint reduction. Experimental results demonstrate that MERSEM reduces SLA violations by up to 45% and carbon emissions by up to 12% compared to state-of-the-art approaches.

Abstract

Graph analytics powers modern intelligent systems such as smart cities, cyber-physical infrastructure, IoT security, and large-scale social networks. As these workloads scale in complexity, their execution in heterogeneous edge-cloud environments results in higher energy use and carbon emission footprint. To address this challenge, we propose MERSEM, a multi-objective evolutionary reinforcement learning framework for sustainable edge-cloud system management. MERSEM integrates evolutionary search with reinforcement learning (RL) to solve the problem of graph workload allocation and scheduling. The evolutionary component explores diverse global solutions, while the RL agent refines decisions through adaptive local optimization. The framework is designed to jointly minimize service-level agreement (SLA) violations and carbon emissions by considering dynamic carbon intensity, resource heterogeneity, and workload characteristics. Experimental results demonstrate that MERSEM outperforms the state-of-the-art with up to 45% SLA violation reductions and up to 12% carbon emission reductions.

Problem

• graph analytics
• edge-cloud systems
• carbon emissions
• SLA violations
• sustainable computing

Innovation

• evolutionary reinforcement learning
• graph analytics
• sustainable computing
• edge-cloud systems
• carbon-aware scheduling