Joint Vehicle Connection and Beamforming Optimization in Digital Twin Assisted Integrated Sensing and Communication Vehicular Networks

TL;DR

The paper addresses joint vehicle connection and predictive beamforming in a DT-enabled ISAC vehicular network with two RSUs. It employs an EKF-based DT to track moving vehicles, predicts their next-slot states, and formulates a non-convex optimization to maximize sum-rate under a PCRB-based sensing accuracy constraint. Solutions include greedy and heuristic algorithms, augmented by a bi-directional LSTM network to predict beamforming and RSU assignments efficiently, achieving near-heuristic performance with reduced complexity. The results demonstrate DT-enabled centralized planning improves throughput and sensing robustness, with potential extensions to larger RSU deployments and handover scenarios.

Abstract

This paper introduces an approach to harness digital twin (DT) technology in the realm of integrated sensing and communications (ISAC) in the sixth-generation (6G) Internet-of-everything (IoE) applications. We consider moving targets in a vehicular network and use DT to track and predict the motion of the vehicles. After predicting the location of the vehicle at the next time slot, the DT designs the assignment and beamforming for each vehicle. The real time sensing information is then utilized to update and refine the DT, enabling further processing and decision-making. This model incorporates a dynamic Kalman gain, which is updated at each time slot based on the received echo signals. The state representation encompasses both vehicle motion information and the error matrix, with the posterior Cramér-Rao bound (PCRB) employed to assess sensing accuracy. We consider a network with two roadside units (RSUs), and the vehicles need to be allocated to one of them. To optimize the overall transmission rate while maintaining an acceptable sensing accuracy, an optimization problem is formulated. Since it is generally hard to solve the original problem, Lagrange multipliers and fractional programming are employed to simplify this optimization problem. To solve the simplified problem, this paper introduces both greedy and heuristic algorithms through optimizing both vehicle assignments and predictive beamforming. The optimized results are then transferred back to the real space for ISAC applications. Recognizing the computational complexity of the greedy and heuristic algorithms, a bidirectional long short-term memory (LSTM)-based recurrent neural network (RNN) is proposed for efficient beamforming design within the DT. Simulation results demonstrate the effectiveness of the DT-based ISAC network.

Figures (11)

• Figure 1: The considered vehicle network with 2 RSUs and $K$ vehicles.
• Figure 2: The block diagram of the DT-based beamforming design and vehicle assigning in an ISAC system.
• Figure 3: The kinematic model of a moving vehicle in the network.
• Figure 4: The bi-directional convolutional LSTM architecture for beamforming optimization.
• Figure 5: The evolution of the accuracy rate after different numbers of training epochs.

Theorems & Definitions (2)

• proof
• proof