Carbon-aware decentralized dynamic task offloading in MIMO-MEC networks via multi-agent reinforcement learning

TL;DR

This paper introduces CADDTO-PPO, a decentralized multi-agent reinforcement learning framework for dynamic task offloading in MIMO-MEC networks, aiming to reduce carbon emissions while maintaining system performance.

Contribution

It proposes a scalable, decentralized architecture with a carbon-first reward strategy for green energy-aware task offloading in dense IoT networks.

Findings

Outperforms DDPG and Lyapunov baselines in reducing carbon intensity.

Achieves near-zero packet overflow under extreme traffic loads.

Maintains constant $O(1)$ inference complexity for lightweight deployment.

Abstract

Massive internet of things microservices require integrating renewable energy harvesting into mobile edge computing (MEC) for sustainable eScience infrastructures. Spatiotemporal mismatches between stochastic task arrivals and intermittent green energy along with complex inter-user interference in multi-antenna (MIMO) uplinks complicate real-time resource management. Traditional centralized optimization and off-policy reinforcement learning struggle with scalability and signaling overhead in dense networks. This paper proposes CADDTO-PPO, a carbon-aware decentralized dynamic task offloading framework based on multi-agent proximal policy optimization. The multi-user MIMO-MEC system is modeled as a Decentralized Partially Observable Markov Decision Process (DEC-POMDP) to jointly minimize carbon emissions and buffer latency and energy wastage. A scalable architecture utilizes decentralized execution with parameter sharing (DEPS), which enables autonomous IoT agents to make fine-grained power control and offloading decisions based solely on local observations. Additionally, a carbon-first reward structure adaptively prioritizes green time slots for data transmission to decouple system throughput from grid-dependent carbon footprints. Finally, experimental results demonstrate CADDTO-PPO outperforms deep deterministic policy gradient (DDPG) and lyapunov-based baselines. The framework achieves the lowest carbon intensity and maintains near-zero packet overflow rates under extreme traffic loads. Architectural profiling validates the framework to demonstrate a constant $O(1)$ inference complexity and theoretical lightweight feasibility for future generation sustainable IoT deployments.