The new energy is connected to the distribution network in the form of distributed generation, which brings uncontrollability, randomness and volatility to the system. With the help of modern power electronics, information and communication and automatic control technologies, the active distribution network with flexibility and controllability has become a development trend. The active distribution network planning is one of the major research fields in recent years. Based on the research results in this field at home and abroad, the research contents and methods of active distribution network planning were summarized, analyzed and prospected. The basic structure of the active distribution network was described, and the characteristics of the components of the distribution network were introduced. According to the different control variables, the planning models of active distribution network were classified, the optimization objectives in the model were summarized. The commonly used model solving algorithms and their advantages and disadvantages were analyzed and summarized. Through the discussion of key issues, the development trend of active distribution network in the future was analyzed.

With the accelerating construction of new power system and popularity of active renewable distributed energy，passive distribution networks are moving towards active distribution networks quickly.However，renewable power is intermittent and uncontrollable，and the penetration of high-proportion renewable energy has brought serious threats to the safe and reliable operation of networks.Active distribution network is an effective solution for large-scale distributed energy grid connection and distribution network optimal operation.To maintain the optimal operation state of the power grid， scholars have conducted extensive researches about active distribution network management.The hot issues in this field include active distribution network planning，active distribution network intelligent decision-making，active distribution network power supply restoration and active distribution network load management. The progress made in these key technologies and the status quos of active distribution networks at home and abroad are analysed. And the analysis results show that the robust planning for active distribution networks taking uncertainties and temporal and spatial correlations into consideration is the development direction for the following studies.

In the context of building a new power system with new energy as the main body，knowledge graph（KG），a large-scale visual semantic network，is expanding its applications rapidly in power operation and inspection. The applications of KG in power operation and inspection mainly focus on semantic information processing. However，a large amount of heterogeneous data will be generated in power grid operation，being able to uphold the construction of multimodal knowledge graph（MMKG） which provides data support for various downstream tasks. In view of functional requirements on electric power inspection， MMKG is introduced to support the intelligent query answering system and fault handling. Expounding the construction technology of MMKG for power inspection data，the scenarios of power operation and inspection that MMKG can give full play in are summarized，and the development direction is forecasted. Finally，the challenges that will be faced by MMKG is analyzed comprehensively，which provides a reference for the development of intelligent power operation and inspection.

In order to solve the problem that the existing transmission network planning methods are not flexible enough in multiple scenarios, and to improve the operation efficiency of the planning methods, this paper proposes a transmission network planning method based on deep reinforcement learning. Firstly, this paper uses scenario information entropy to generate a variety of typical scenarios, and establishes a flexible transmission network planning model suitable for multiple scenarios. Secondly, an improved pointer network model suitable for transmission network planning is proposed by using the deep reinforcement learning method and the actor critical method, and the revised pointer network with Actor-Critic (RPNAC) method is used to solve the planning model. Finally, an example verifies the effectiveness and feasibility of the proposed method.

[Objective] This paper summarizes the knowledge graph completion methods based on graph neural network through research and literature review. [Coverage] With “knowledge graph completion” as search terms to retrieve literature from the Web of Science, DBLP and CNKI, a total of 79 representative literature were screened out for review. [Methods] Based on the model structure, three knowledge graph completion methods based on graph neural networks were summarized, including graph convolutional neural networks, graph attention networks, and graph auto encoder. [Results] Using common data sets and evaluation indicators for knowledge graph completion tasks, the effects of various models were comparatively analyzed in terms of MRR, MR, Hit@k and other performance evaluations, and prospects for future research were suggested. [Limitations] In the comparison of experimental results, only the evaluation results of some widely used models on the FB15K-237 and WN18RR datasets are discussed, the comparison of all models on the same dataset is lacking. [Conclusions] Compared with the representation learning model and the neural network model, the graph neural network model has better performance, but it still faces difficulties such as high complexity of model relationships, over-smoothness, and poor scalability and universality.