The advancement of autonomous driving technology has brought significant benefits to modern transportation systems. However, individual autonomous vehicles face challenges such as limited perception range and insufficient autonomous capabilities. Cooperative groups of autonomous vehicles, enabled by advanced communication technologies, can enhance traffic efficiency through information exchange. Existing research primarily focuses on centralized autonomous vehicle groups, where the leading node suffers from weak resilience and high computational load, making it difficult to maintain group collaboration over time. To address these issues, this article proposes a decentralized formation and self-adaptation method for autonomous vehicle social groups based on consensus resistance in closed scenes. First, we introduceconsensus resistanceas a metric to evaluate social group and member consistency, and develop a decentralized formation approach. Second, we present a self-adaption model for autonomous vehicle social groups, incorporating four evolutionary events: 1) expansion; 2) merging; 3) reduction; and 4) splitting, to ensure the stability of moving social groups. Simulation results demonstrate the proposed method effectively constructs social groups in both real-world and simulated environments, exhibiting robust consistency throughout the self-adaption process.

By reducing the size of transmitted data between device-side and edge-side machine learning model parts, intermediate activation (IA) compression can alleviate communication overhead, lower latency, and conserve energy, thus enhancing the model partitioning in edge-device collaborative inference scenarios. However, existing studies lack refined resource allocation and fail to jointly optimize edge-device communication and computing resources, especially in terms of IA compression rates, leading to sub-optimal inference performance. To this end, we propose an adaptive model partitioning, intermediate activation compression, and resource allocation scheme for efficient edge-device collaborative inference. We jointly optimize the model partitioning point selection, IA compression rates control, computing resource allocation for both edge and devices, and device transmission power allocation. Our goal is to minimize the weighted sum of inference accuracy loss, inference latency, and device energy consumption. To solve the high-complexity optimization problem efficiently, we design a DRL-based algorithm, which decouples the problem into sub-problems firstly, and then employs an SD3 (Softmax Deep Double Deterministic Policy Gradients)-based DRL method to solve the partitioning point and IA compression rates sub-problem, and utilizes various numerical methods to solve the sub-problems of local and edge computing resource allocation and transmission power control. Extensive comparative simulations with four different schemes under different environmental parameters demonstrate the superiority and robustness of our approach.

Vehicle edge computing (VEC) acts as an enhancement to provide low latency and low energy consumption for internet of vehicles (IoV) applications. Mobility of vehicles and load difference of roadside units (RSUs) are two important issues in VEC. The former results in task result reception failures owing to vehicles moving out of the coverage of their current RSUs; the latter leads to system performance degradation owing to load imbalance among the RSUs. They can be well solved by exploiting flexible RSU-RSU cooperation, which has not been fully studied by existing works. In this paper, we propose a novel resource management scheme for joint task offloading, computing resource allocation for vehicles and RSUs, vehicle-to-RSU transmit power allocation, and RSU-to-RSU transmission rate allocation. In our scheme, a task result can be transferred to the RSU where the vehicle is currently located, and a task can be further offloaded from a high-load RSU to a low-load RSU. To minimize the total task processing delay and energy consumption of all the vehicles, we design a twin delayed deep deterministic policy gradient (TD3)-based deep reinforcement learning (DRL) algorithm, where we embed an optimization subroutine to solve 2 sub-problems via numerical methods, thus reducing the training complexity of the algorithm. Extensive simulations are conducted in 6 different scenarios. Compared with 4 reference schemes, our scheme can reduce the total task processing cost by 17.3%-28.4%.