Active Beyond-Diagonal RIS Empowered Heterogeneous Edge Computing: A Distributional Reinforcement Learning Approach

2026-07-14

AI Summary

This work addresses the energy-delay trade-off and high-dimensional mixed-integer nonconvex joint optimization challenge arising from inter-sector energy leakage in heterogeneous mobile edge computing systems assisted by reciprocal bi-directional reconfigurable intelligent surfaces (BD-RIS). To tackle this, the authors propose an end-to-end collaborative optimization framework that jointly determines task offloading decisions, CPU/GPU computational resource allocation, transmit power, receiver processing, and BD-RIS configuration. They innovatively design a distributional soft actor-critic algorithm, DSAC-T, which enhances policy robustness under reward heterogeneity and constraint boundaries by explicitly modeling the return distribution. Experimental results demonstrate that DSAC-T significantly outperforms baseline methods in terms of energy-delay performance, achieves a feasible solution ratio of 81.67%, and requires only 0.0267 seconds for online decision-making in a single scenario.

Abstract

Active beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) enables hybrid transmitting and reflecting mode to achieve effective signal amplification and full-space coverage, thus providing a promising solution for blockage-aware uplink offloading in heterogeneous mobile edge computing (MEC) systems. However, practical hybrid mode active BD-RIS are realized by reciprocal devices, which inherently generate cross-sector energy leakage that will reshape the system-level energy-latency tradeoff. This paper studies energy-aware offloading and resource allocation for reciprocal active BD-RIS-assisted heterogeneous MEC, where offloading decisions, CPU/GPU computation allocation, transmit powers, receive processing, and active BD-RIS are tightly coupled. The resulting problem is a high-dimensional mixed integer nonconvex problem and is difficult to solve efficiently by conventional per-instance optimization. To address this challenge, we develop an end-to-end joint optimization framework based on a refined version of the distributional soft actor--critic algorithm, named as DSAC-T. By modeling return distributions rather than only expected values, DSAC-T improves policy stability under reward heterogeneity and feasibility-boundary sensitivity. Compared with other baseline algorithms, DSAC-T achieves the best energy-latency reward, the highest feasibility ratio of 81.67%, and a fast online decision time of 0.0267 s per scenario.

Problem

• Reconfigurable Intelligent Surface
• Mobile Edge Computing
• Energy-Latency Tradeoff
• Task Offloading
• Resource Allocation

Innovation

• Active BD-RIS
• Distributional Reinforcement Learning
• Heterogeneous MEC
• Energy-Latency Tradeoff
• DSAC-T