Digital Twins Meet Open RAN: Case Studies, Implementation, and Opportunities

Mobile communication technology is evolving to dedicated ubiquitous connections for the massive Internet of Things (IoT) devices. With the goal of ubiquitous connections, mobile operators are exploring feasible solutions to improve the network service efficiency for diverse application scenarios with different requirements. In this context, the open radio access network (Open RAN) is an attractive solution with flexible openness and high intelligence advantages. However, it is challenging to implement dynamic resource scheduling with the RAN intelligent controller (RIC) for flexible service provisions due to the high computing overhead involved in diverse machine learning methods. To address the issue, we developed a digital twin (DT)-based Open RAN system where the RICs can implement risk-free measurements in a virtual space. It can significantly reduce the cost of trial-and-error and improve the quality of services to further open the RAN in diverse 5G and beyond scenarios. We selected two key metrics, the energy consumption and the round-trip delay, to verify the effectiveness of our DT Open RAN system for non-real-time (Non-RT) and near-real-time (Near-RT) applications, respectively. The experiment results demonstrate that our system achieves the performance of low-energy networks and low-latency data transmission.