Search

• A STGCN-based DDQN framework (namely STGCN-DDQN) is presented. • The STGCN-DDQN can capture spatio-temporal changes in power system stability control. • The control strategy based on severely disturbed units identification and STGCN-DDQN. • Severely disturbed units as action space, the STGCN-DDQN quickly finds the solution. • The simulation results prove the advantage of STGCN-DDQN method in stability control. With increasing uncertainties and complexity in modern power system, it is still very challenging to figure out a cost-effective emergency control strategy that can reliably react to the spatio-temporal variations. Faced with this challenge, this paper presents a power system emergency control strategy based on severely disturbed units identification and STGCN-DDQN (Spatio-Temporal Graph Convolutional Network -Double Deep Q-Network). Inspired by the novel combination of STGCN for spatio-temporal features extraction and DDQN for decision making, the STGCN model helps the DDQN agent to better capture spatio-temporal features when dealing with topology variations. Considering the problem of combination explosion, the severely disturbed units are chosen as action objects of STGCN-DDQN, which makes the agent quickly find the optimal solution. Further, the algorithm of emergency control strategy is designed based on the close combination of severely disturbed units identification and STGCN-DDQN. Finally, by building multiple test scenarios, the proposed method is verified based on the New England 39-bus standard system and Northeast China power system. The simulation results demonstrate that the proposed method outperforms the other schemes in terms of control performance when considering topology variations, modeling errors, power flow conditions and random noise. [ABSTRACT FROM AUTHOR]

• Weak horizontal and vertical transmission channels are defined. • A power flow adjustment strategy that can fasten the adjustment processing is formulated. • The prior probability of action is given to improve learning efficiency. • A deep reinforcement learning model suitable for power flow adjustment is established. To solve the problem of human resources and time consumption caused by unsolvable power flow of weak power grid, an adjustment method for unsolvable power flow based on weak transmission channels and deep reinforcement learning (DRL) is proposed. Weak horizontal and vertical channels are defined, and their relationship with unsolvable power flow is demonstrated. Then, based on the idea of reducing the load level first and then gradually recovering it, actionable device and action margin are determined based on transmission channel positioning, adjustment sensitivity and solvability degree, so as to form a power flow adjustment strategy. Next, the Markov decision-making process of power flow adjustment is constructed, the prior probability of action is given by adjustment sensitivity of the actionable device, and the action is mapped to the adjustment amounts of generators and capacitors/reactors. Based on soft actor-critic, a DRL model suitable for power flow adjustment is established. Finally, the simulation results show that the proposed method performs well both in the New England 39-bus standard system and an actual power grid of China. Compared with the results obtained by other methods, the superiority of the proposed method is verified. [ABSTRACT FROM AUTHOR]

• A comprehensive evaluation on power flow solvability guides the search direction of learning. • Combining GCN and RNN to extract the spatial-temporal information makes the learned information more valuable. • Action space of reinforcement learning is narrowed according to knowledge. • For actual power system, transmission channel off-limit is a key factor for unsolvable problem. In view of the problem of manpower and time consumption caused by unsolvable power flow in current AC / DC hybrid power grid with new energy, a power flow state assessment and solvability recovery adjustment method based on graph convolutional recurrent neural network (GCRNN) and deep double Q-learning network (DDQN) is proposed. First, active power balance degree, reactive power balance degree and channel transmission margin are defined and weighted together to evaluate the solvability of power flow. Then, a power flow state evaluation model based on GCRNN is proposed by combining graph convolution with recurrent neural network, where the input is tangent vector of power flow equations, and the output is comprehensive evaluation index of solvability. Next, the state space, action space and multiple rewards of deep reinforcement learning are formed. By introducing the search direction, learning information extraction and search space constraints, an automatic adjustment method to restore power flow solvability is designed. Finally, the simulation results show that the proposed method performs well both in New England 39-bus standard system and actual power grid of China. Compared with the results obtained by other methods, the superiority of the proposed method is verified. [ABSTRACT FROM AUTHOR]