Summary To enhance the resilience of distribution systems and fight against extreme disasters, a novel planning‐attack‐reconfiguration optimization method is proposed in this paper. Firstly, according to the processes of prevention, defence, and restoration for a resilient distribution system through disruption, the novel resilience evaluation indicators are presented, which include the node degree of distributed generation (DG) bus, survival rate, and recovery ability. Secondly, a novel planning‐attack‐reconfiguration optimization model is developed to improve the resilience of distribution systems. In DG planning stage, the multi‐objective planning model is formulated, which includes the minimization of the total cost of investment and operation, and the maximization of the node degree of DG buses for critical loads. In the attack stage, a clear worst case of N‐k contingencies on the basis of generalized nodes is presented to reduce the computational complexity. Then, the post‐disaster network reconfiguration model is formulated to maximize the restoration rate of critical loads (RRCL). Finally, the proposed method is illustrated by the case study on PG&E 69‐bus distribution system. The simulation results indicate that all the RRCL can reach about 90% in the four multipoint fault scenarios. Meanwhile, other evaluation indicators are greatly improved. It is shown that the resilience of distribution systems can be dramatically enhanced by the proposed method.

Background Due to the high cost of data collection for magnetization detection of media, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer (PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. Method In this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML’s gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness. Results The average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model. The loss value of the meta-learning optimization model in the iterative process drops the fastest and steadily compared to the MAML model and the LSTM model. In cross-domain experiments, the average accuracy of the meta-learning optimized model can still reach 0.833. Conclusions In the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model. And in the training of cross-domain datasets, this model performs best.

BackgroundDue to the high cost of data collection and labeling for magnetization detection of medium, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer(PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. MethodIn this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML's gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness.ResultsThe average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model.ConclusionsIn the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model.