Chunsheng Chen

With the direct impact on the smooth operation of active distribution networks of distributed power sources, power grid enterprises urgently need to build sensitive energy data identification technology. This study proposes a sensitive energy data identification model and technologies for structured datasets based on theoretical knowledge such as information theory and clustering analysis. Firstly, energy data sensitivity quantification technology based on information entropy is constructed , which calculates the sensitivity of each data attribute using the data attribute entropy, maximum discrete entropy, and sensitivity definition formula. Secondly, sensitivity clustering algorithm technology based on k-means to aggregate is constructed, which analyzes energy big data center datasets and perform sensitive data desensitization operations. Thirdly, sensitive attribute recognition technology based on association rule is constructed, which optimizes the recognition effect of sensitive information attributes in energy big data centers at the dataset level.

Cooperative coordination at unsignalized road intersections, which aims to improve the driving safety and traffic throughput for connected and automated vehicles, has attracted increasing interests in recent years. However, most existing investigations either suffer from computational complexity or cannot harness the full potential of the road infrastructure. To this end, we first present a dedicated intersection coordination framework, where the involved vehicles hand over their control authorities and follow instructions from a centralized coordinator. Then a unified cooperative trajectory optimization problem will be formulated to maximize the traffic throughput while ensuring the driving safety and long-term stability of the coordination system. To address the key computational challenges in the real-world deployment, we reformulate this non-convex sequential decision problem into a model-free Markov Decision Process (MDP) and tackle it by devising a Twin Delayed Deep Deterministic Policy Gradient (TD3)-based strategy in the deep reinforcement learning (DRL) framework. Simulation and practical experiments show that the proposed strategy could achieve near-optimal performance in sub-static coordination scenarios and significantly improve the traffic throughput in the realistic continuous traffic flow. The most remarkable advantage is that our strategy could reduce the time complexity of computation to milliseconds, and is shown scalable when the road lanes increase.