Integration of 6G Signal Processing, Communication, and Computing Based on Information Timeliness-Aware Digital Twin

Abstract

6 G has emerged as a feasible solution to enable intelligent electric vehicle (EV) energy management. It can be further combined with digital twin (DT) to optimize resource management under unobservable information. However, the lack of reliable information timeliness guarantee increases DT inconsistency and undermines resource management optimality. To address this challenge, we investigate DT-empowered resource management from the perspective of age of information (AoI) optimization. We utilize AoI as an effective information timeliness metric to measure DT consistency, and construct an AoI-optimal DT (AoIo-DT) to assist resource management by providing more accurate state estimates. A joint optimization algorithm of signal processing, communication, and computing integration based on AoI-aware deep actor critic (DAC) with DT assistance is proposed to achieve balanced tradeoff between DT consistency and precision improvement of EV energy management. It further improves learning convergence and optimality of DAC by enforcing training with data samples of smaller AoI. Numerical results verify its performance gain in AoI minimization and EV energy management optimization.