Virtual power plant (VPP) plays an important role in improving the balance and regulation abilities of new power system. The safe and reliable operation is support by the VPP end-to-end communication network with differentiated multi-service bearing capability. For the requirement of unified and standard VPP end-to-end networking scheme, the VPP service communication metrics, as well as the communication network architecture of VPP aggregation and control are analyzed. Then, a multi-dimension hierarchical VPP end-to-end network evaluation index system is put forward. In addition, an end-to-end VPP network evaluation method considering differentiated time-sensitive and granular requirements of multiple services is proposed. Finally, the suitability analysis results of various end-to-end networking schemes and multiple services with differentiated time-sensitive and granular requirements are given, which plays a guiding role in establishing a unified standard VPP end-to-end networking scheme.

With the development of science and technology, the intelligent distribution network is making rapid progress and the demand for power supply is also increasing. The classification and analysis of the power outage causes in distribution network is helpful to the prediction of power failure. There is a large gap in the proportion of categories of the sample data of power grid outage causes, and serious category imbalance will lead to the deviation of classification results. In order to classify the original data more reasonably, the sample value added technology based on generative adversary network is used to expand the category data with less data in this paper. In order to realize automatic classification of power grid outage causes, the method of text data preprocessing and the text classification model based on deep learning are studied. Finally, the experimental results show the influence of sample capacity and classification accuracy.

The integration of volatile distributed energy resources (DERs) brings new challenges for the active distribution network maintenance scheduling (DN-MS). Conventionally, the DN-MS is formulated as a deterministic optimization model without considering the uncertainties of DERs. In this paper, the DN-MS is formulated as a multistage stochastic optimization problem, which is cast as a stochastic mixed-integer nonlinear programming model. It aims to reduce the total maintenance cost constrained by the reliability indices. To capture the operational characteristics of active distribution networks, the uncertainties of DERs and post-outage operation strategies of switching devices are incorporated into the model. In general, this type of model is intractable and mainly solved by heuristic search methods with low efficiency. Recently, Monte-Carlo tree search (MCTS) is emerging as a scalable and promising reinforcement learning approach. We propose a stochastic MCTS solution to this problem. In the tree search procedure, a sample average approximation technique is developed to estimate multistage maintenance costs considering uncertainties. To speed up the MCTS, the complicated constraints of the original problem are transformed to penalty or heuristics functions. This approach can asymptotically approximate the optimum with promising computation efficiency. Numerical test results demonstrate the superiority of the proposed method over benchmark methods.

In recent years, with the rapid growth of distributed generation, the load pressure of distribution transformer is also increasing, and power fail occurs frequently. Therefore, this paper studies a distribution transformer health early warning system based on EDC-GRU network. Firstly, we clarify the design idea of the system. Secondly, we define all the architecture and function. Finally, the result shows that our system can predict the future health status of distribution transformer, through the analysis of the operation data of each distribution transformer and make the early warning in time, which can inform people to take corresponding measures so as to reduce the failure rate, and maintain the health status of the distribution network.

Firstly, the positioning and function of energy switches in regional energy internet are described, and a typical infrastructure and control strategy of eight-port intelligent microgrid energy switches are proposed. Then paper verifies the correctness of the control strategy by PSCAD simulation. The characteristics and advantages of energy switches in practical application are pointed out, which provides effective support for the construction of regional energy internet in the future.

In order to improve the flexibility and reliability index of distribution network, a certain number of segments and tie switches are needed. The main function is to minimize the outage area when the power outage, or load exchange between different roads. Without considering the reliability of the switch itself under the condition of the sectionalizing and tie switches allocation more reliability of power during operation is higher, but at the same time, the more the number of switch configurations, the power grid construction cost is higher. In the process of power grid construction, it is necessary to pay more economic cost in order to obtain higher reliability. This article embarks from the reality, in the study of dynamic programming method for distribution network based on switch configuration algorithm, combined with the characteristics of distribution network construction, contact switch configuration optimization section, distribution network is put forward, and the actual grid optimization experiment, verify the correctness of the method.

The Energy Internet, featuring in-depth integration of renewable energy and internet information technology, is the future orientation of the energy industry. This paper breaks through the former studies on energy efficiency which only concentrate on one form or one section of energy. Based on the second law of thermodynamics, it analyzes and proposes five kinds of energy efficiency evaluation indexes from the energy sections of production, transmission, consumption, storage and conversion. It provides guidance to top-level design, project acceptance and optimization of Energy Internet.

Este libro, coordinado por los profesores Liu Wei y Su Jian, es una recopilación de artículos que recoge las investigaciones sobre la situación económica y financiera de China realizadas por el profesor Liu y sus colegas. En la nueva era de la economía china, los autores destacan la importancia de una reforma completa para su desarrollo. Con base en su teoría sobre la gestión de la oferta y la reforma de la oferta, efectuaron un análisis amplio del futuro de la operación económica y financiera del país. Entre sus temas se encuentran la operación y la gestión de la macroeconomía china, el desarrollo de unidades micro, la interacción entre reforma y desarrollo económico, la lógica y la práctica de la reforma estructural de la oferta, el mercado de capital y otros aspectos relevantes. Los lectores a los que se dirige esta obra son estudiantes, profesionales, encargados de formular políticas públicas e investigadores en las áreas de economía y finanzas.

Heterogeneous characteristics of a big data system for intelligent power distribution and utilization have already become more and more prominent, which brings new challenges for the traditional data analysis technologies and restricts the comprehensive management of distribution network assets. In order to solve the problem that heterogeneous data resources of power distribution systems are difficult to be effectively utilized, a novel generative adversarial networks (GANs) based heterogeneous data integration method for intelligent power distribution and utilization is proposed. In the proposed method, GANs theory is introduced to expand the distribution of completed data samples. Then, a so-called peak clustering algorithm is proposed to realize the finite open coverage of the expanded sample space, and repair those incomplete samples to eliminate the heterogeneous characteristics. Finally, in order to realize the integration of the heterogeneous data for intelligent power distribution and utilization, the well-trained discriminator model of GANs is employed to check the restored data samples. The simulation experiments verified the validity and stability of the proposed heterogeneous data integration method, which provides a novel perspective for the further data quality management of power distribution systems.

Feeder system is an important part of the distribution system, which is not only shouldering the mission of fulfilling social responsibility, but also related to economic benefit of power supply companies. In the traditional planning method of feeder system, power supply reliability is implicitly reached by “N-1” criterion, but it is not particularly effective in reducing costs and handling budgets. Therefore, this planning method does not meet distribution network differentiation and meticulous management requirements and it's difficult to protect the interests of power supply companies and consumers, unable to adapt to future development needs of distribution network. In this paper, based on the different requirements for power supply reliability in different regions, the key elements of feeder system (feeder capacity, zone, segmentation, protection, switching time, etc.) and their flexible configuration method were proposed. Based on coordination accident support capacity of different zone switching mode and transfer capability for feeder system, feeder system planning method that supports feeder layer outage, transformer outage and substation outage and the overall process of feeder system reliability design were put forward, to ensure planning scheme achieve satisfactory electrical performance, accident control, optimal power supply reliability and economy. Finally, distribution network optimal planning in high reliability demonstration area of a city was selected as an actual case and satisfied planning scheme was obtained, to verify the effectiveness of the proposed planning methods.

With active management, lower network loss, higher reliability, the active distribution network is one of the future trends of the distribution network. This paper establishes multi-objective optimization planning model for the active distribution network. The comprehensive optimal scheme is analyzed in three objects: the investment cost, the network loss, and the system reliability. Based on the Pareto optimization method, the paper proposes the multi-objective optimization planning algorithm, then the final planning scheme is determined. Through the simulation results of the IEEE 33 standard model, the validity and rationality of the model is verified.

Principal component analysis is performed on the operation and management evaluation of smart distribution network because of its objectivity, synthesis and simplification to original data information. According to the demand on the evaluation that focuses on intellectualization and reliability of distribution network, an index system for intelligent and reliable evaluation is built. The performance indicators and the principal component analysis are used to analyze the intelligent and reliable level of distribution network operation and management. The feasibility of the evaluation index system is verified by the evaluation results of some distribution networks.

Middle and long term load forecasting is the essential basis for planning of distribution network. With high penetration DGs (distributed generation) integrated into network, the net load demand of HV/MV network become more complicated, load forecasting encounters greater challenge than ever. Volatility and intermittency of wind and solar power has greatly influenced the load characteristics. A new middle and long term load forecasting method for distribution network with DGs is proposed in this paper, which concerns time-varying characteristic of DG output power. Firstly, we get the conventional spatial load forecasting results. Then, we get yearly time-varying curves of DG output using Monte Carlo simulation. Lastly, superposing time-varying curves of conventional load and DGs, we can get the net-load forecasting result for distribution network, which is more accurate than ever.

Currently, China has just started micro-grid development, and has not yet formed a mature commercial operation mode, by study of foreign micro-grid operation mode and domestic micro-grid development, this article will introduce four micro-grid operation modes applicable to China, including grid operation mode, investors operation mode, joint operation mode, users operation mode, and analyze the different trade and settlement modes. Key factor affecting micro-grid investment income is the cost, covering body cost, grid-connection cost and maintenance cost. Technical and economic analysis of micro-grid consists of power system computation, micro-grid system optimization and investment revenue analysis. This paper will mainly analyze the investment revenue of micro-grid project, calculate the cost of investment, pay back period, electricity cost of three micro grids, covering a city micro grid, a remote area micro-grid and an island stand-alone micro-grid, at last, it will analyze the features, advantages and disadvantages.

With the purpose of providing adequate electric energy to consumers and maintaining the economy during the implementation of reliable power supply, the standard of power supply security for urban power network is drawn up. The N?1 contingency criterion is improved by the relationship between the group demand and security of power supply in the Engineering Recommendation P2/6 (ER P2/6). That means the simple 'qualitative' evaluation indices of power supply security are developed into detailed 'quantitative' evaluation indices. The differences between security and reliability of power supply as well as their relation are clarified in this paper. The principle of drawing up ER P2/6 is dissected and on this basis standard of power supply security for urban power network in China is drafted. The conclusion is available for reference to the planning and operation of urban power networks in China.

Scientific and rational evaluation indices of urban power network performance are the guarantee of carrying on evaluation work regularly and objectively.This paper analyzes existed problems of present indices, presents design principle and framework of evaluation indices of urban power network performance,explains this framework indices in detail and compares with the ones abroad,meanwhile proposes some specific suggestions for the evaluation work of urban power network in China.

Abstract—The indices of performance evaluation are important for assessing the development level of urban power network. A framework of indices about performance evaluation for urban power network, including 7 basic indices, 14 technical indices and 6 economic indices, is put forward in this paper. Ratio of transformer capacity, ratio of line length and ratio of transformer capacity to line length are proposed initially to evaluate the rationality of network construction. Investment per unit load and operation cost per unit power energy are adopted to evaluate the economic level ofconstruction and operation. The definitions and reasonable scopes of indices about performance evaluation are explained in detail. Based on the above indices, weakness and developing targets of urban power network in China are analyzed, and results show that the indices proposed and summarized are effective and practical. Key words: urban power network; evaluation index; ratio of transformer capacity; ratio of line length; ratio of transformer capacity to line length