A Monte Carlo tree search-based method for decision making of generator serial restoration sequence

Abstract

Reasonable generator serial restoration sequence is a key issue to the system restoration following blackouts. This paper proposed an optimization method for the decision making of generator serial restoration sequence based on Monte Carlo tree search algorithm. First, the generator serial restoration sequence mechanism during the restoration process is analyzed. Considering the maximization of the total power generation capacity as the objective function, this paper also consider generator’s hot start. Second, the Monte Carlo tree search algorithm (MCTS) is applied to decide the generator serial restoration sequence. In the simulation stage of MCTS, the Dijkstra’s algorithm is utilized to determine the shortest path between the selected generator and the recovered power system. Finally, the IEEE 39 bus system and Hebei power grid system are used to validate the proposed algorithm. Simulation results show that the proposed method is efficiency and it can provide an reasonable generator serial restoration sequence to maximizing power generation during the restoration process.

Bi-Level Planning of Electric Vehicle Charging Stations Considering Spatial–Temporal Distribution Characteristics of Charging Loads in Uncertain Environments

“…We use the LHS to sample and obtain the behavioral characteristic indexes such as initial location, time of going to work, time of going out of work, initial SOC, and driving speed of cabs and online car-hailings. Based on obtaining the OD matrix of each EV, a real-time Dijkstra algorithm is used for path guidance to search for the shortest path between ODs [33]. The flow of Dijkstra's algorithm is shown in Figure 2, where Vi stands for the starting node, V j refers to the target node, Set O is used to hold unexamined nodes, and Set D is used to hold the examined nodes.…”