Microgrids incorporated with distributed generation (DG) units and energy storage (ES) devices are expected to play more and more important roles in the future power systems. Yet, achieving efficient distributed economic dispatch in microgrids is a challenging issue due to the randomness and nonlinear characteristics of DG units and loads. This paper proposes a cooperative reinforcement learning algorithm for distributed economic dispatch in microgrids. Utilizing the learning algorithm can avoid the difficulty of stochastic modeling and high computational complexity. In the cooperative reinforcement learning algorithm, the function approximation is leveraged to deal with the large and continuous state spaces. And a diffusion strategy is incorporated to coordinate the actions of DG units and ES devices. Based on the proposed algorithm, each node in microgrids only needs to communicate with its local neighbors, without relying on any centralized controllers. Algorithm convergence is analyzed, and simulations based on real-world meteorological and load data are conducted to validate the performance of the proposed algorithm.

With the acceleration of urbanization in the world, urban traffic congestion has become an urgent challenge in most cities. Adaptive traffic signal control is the most approved control method to solve the problem, and accurate real-time traffic information is critical to this solution. This paper presents distributed cooperative reinforcement learning-based traffic control that integrates V2X networks’ dynamic clustering algorithm. To obtain traffic flow information accurately and instantaneously, it is important to improve the cluster stability in V2X networks. A dynamic clustering algorithm is proposed based on the enhanced affinity propagation. The proposed clustering algorithm introduces the initial cluster partition to maintain a proper cluster size and adds the lane and destination factors to improve the cluster's stability. The algorithm can provide efficient and accurate traffic state information to traffic signal controls. By integrating the clustering algorithm, a cooperative reinforcement learning control scheme is proposed to balance the traffic load. To address the tough dimensionality curse of reinforcement learning, a distributed mechanism for intersection cooperation is introduced, and a fast gradient-descent function approximation method is proposed to improve the controls’ real-time performance. The proposed intelligent traffic control scheme that integrates the stable clustering algorithm can effectively improve the traffic throughput, reduce the average waiting time, and avoid congestion. Numerical simulations on real scenarios validate the performance of the proposed approach.

Communication resource allocation is important for improving the performance of users in mobile edge computing (MEC) scenarios. In existing studies, the users in the MEC system typically suffer from the unfair resource allocation, which results in the inefficient resource utilization and degraded user performance. To address this challenge, in this paper, we propose a fair resource allocation approach to maximize the overall network throughput, under the constraint of each mobile user’s minimum transmission rate. We formulate the problem as a fair Nash bargaining resource allocation game, and the existence and uniqueness of the solution to this game model are analyzed. By adopting the time-sharing variable, we obtain the near optimal bargaining resource allocation strategy for the mixed integer nonlinear programming optimization. The user’s priority is further considered in the iterative implementation of the proposed algorithm by considering the time delay constraint of users. Simulation results show that the proposed scheme outperforms existing methods in terms of resource allocation fairness and overall system throughput.

Driving style recognition plays a key role in ensuring driving safety and improving vehicle traffic efficiency. With the development of sensing technology, data-driven methods are more widely uesd to recognize driving style. However, adequately labeling data is difficult for supervised learning methods, while the classification accuracy is not sufficiently approved for unsupervised learning methods. This paper proposes a new driving style recognition method based on Tri-CatBoost, which takes CatBoost as base classifier and effectively utilizes the semi-supervised learning mechanism to reduce the dependency on data labels and improve the recognition ability. First, statistical features were extracted from the velocity, acceleration and jerk signals to fully characterize the driving style. The kernel principal component analysis was used to perform nonlinear feature dimension reduction to eliminate feature coupling. CatBoost is an ensemble of symmetric decision trees whose symmetry structure endows it fewer parameters, faster training and testing, and a higher accuracy. Then, a Tri-Training strategy is employed to integrate the base CatBoost classifiers and fully exploit the unlabeled data to generate pseudo-labels, by which the base CatBoost classifiers are optimized. To verify the effectiveness of the proposed method, a large number of experiments are performed on the UAH DriveSet. When the labeling ratio is 50%, the macro precision of Tri-CatBoost is 0.721, which is 15.7% higher than that of unsupervised K-means, 1.6% higher than that of supervised GBDT, 3.7% higher than that of Self-Training, 0.7% higher than that of Co-training, 1.5% higher than that of random forest, 6.7% higher than that of decision tree, and 4.0% higher than that of multilayer perceptron. The macro recall of Tri-CatBoost is 0.744, which is also higher than other methods. The experimental results fully demonstrate the superiority of this work in reducing label dependency and improving recognition performance, which indicates that the proposed method has broad application prospects.

The application of nonorthogonal multiple access (NOMA) technology to New Radio (NR) Vehicles-to-Everything (V2X) can further reduce communication delay and improve the system capacity of the vehicular network. However, due to the high mobility of the vehicles, it is difficult for the base station to obtain the channel information between vehicles in real time for resource allocation and vehicle transmission power control. To this end, we propose a two-stage scheme of centralized resource allocation and distributed power control to meet the NR V2X Mode 1 requirement while NOMA technology is employed in each vehicle group. First, at the beginning of a transmission period, the base station allocates resources to vehicle groups. For this centralized manner, we propose a graph-based matching approach to allocate resources to improve system capacity. Then, each vehicle group controls and adjusts transmission power for NOMA communication in the period. For this distributed manner, we propose a noncooperative game to control the power of the vehicle groups and then analyze the performance of the noncooperative game. Afterward, we further put forward a cooperative game approach to control the power of the vehicle group to increase system capacity. Compared with the noncooperative game, the proposed scheme can increase communication capacity by up to 5% and reduce transmission power consumption by 36%.