This demo presents a digital twin (DT) of an reconfigurable intelligent surface (RIS) wireless system that employs SRL policy optimization for phase adaptation. The demo will demonstrate the efficiency of the spiking reinforcement learning (SRL) against conventional DRL approaches in terms of (i) energy consumption, (ii) training latency reduction, (iii) outage probability, and (iv) bit error rate. The SRL model will retrieve information from a DT that operate in real time. In other words, the audience will have the opportunity to: (i) interact with a time-evolving DT; (ii) see quantified benefits of SRL against conventional DRL; and (iii) observe the impact of the use of RIS coupled with DT and SRL approaches on the performance of the communication system.
Ilias Crysovergis, Stylianos E. Trevlakis, Dimitris Kleitsas, Alexandros-Apostolos A Boulogeorgos, Theodoros A. Tsiftsis, and Dusit Niyato, “A Digital Twin Based Reconfigurable Intelligent Surface Phase Adaptation Using Spiking Reinforcement Learning Policy Optimization”, IEEE International Conference on Machine Learning for Communication and Networking, May, 2025.