State Grid Research Articles

Team Performance Analysis of Provincial Electric Power Company Considering Production Cost

The electric power industry is related to the national livelihood, and regional economic development is closely related to the pillar industry. At present, China's economy continues to develop steadily, and the promotion of domestic industrialization has also increased the demand for electricity. In recent years, the state power industry has made great progress, in order to further adapt to the needs of domestic and foreign market competition, the State Grid has also carried out a systematic reform of its own management system. In the reform process, strengthening the construction of performance appraisal system is a very important change. According to statistics, as of June 2020, the number of employees of State Grid has reached more than 900,000. As the most basic business unit of the state grid, the team is the cell of the state grid. It is the basis for the completion of various production management work and plays an important role in the safe production and stable output of electric power enterprises. Based on the relevant indicators of the work of the team, this paper analyzes the performance of the team through the production cost performance model, and provides suggestions for the optimization of the team for power grid enterprises

Research on Key Issues Concerning the Implementation of Energy Internet Enterprise Strategy

The theoretical system of the State Grid energy internet strategy is studied in this paper. This paper combs the scientific connotation of the State Grid energy Internet strategic goal under the dual carbon goal. Combining the policy requirements of state-owned enterprise reform with the requirements of electric power system reform, a systematic and theoretical understanding has emerged. The scientific connotation of the energy Internet strategic system of the State Grid at the current stage is proposed, which provides theoretical support and practical guidance for relevant departments. The result showed that the State Grid energy Internet strategy system formed a complete system, covering all aspects of enterprise development, connecting the foundation, ability, image and achievements of development, and is highly systematic, scientific and adaptable.

Research on the Business Model of Enterprise Energy Service Based on Digitalization

State Grid e-commerce Co., Ltd. (hereinafter referred to as "State Grid e-commerce company") aims to realize the Internet of core business transactions, and undertakes the important mission of expanding new business areas and cultivating new profit growth points. Through in-depth study of new digital products and business models in the energy service market, expanding the business chain, enhancing the value chain, cultivating new advantages and enhancing new power, the market competitiveness and sustainable development ability of power grid enterprises will be effectively improved, which is a business innovation exploration to actively respond to the reform of power system and the strategic changes of State Grid Corporation.

Key Techniques of the Digital Energy Internet Park: An Example of State Grid Energy Internet Rongchuang Park in Lanzhou

The construction of the digital energy internet is of great significance to the formation of the global energy internet. This paper uses the Rongchuang park of state grid Lanzhou power supply company as an example. Particularly, the key techniques from “source, grid, load, and storage” were summarized. It is key for the building of the energy internet Rongchuang park to increase the proportion of clean energy production and consumption, improve the intelligent level of the power grid, fully tap the potential of load side energy conservation and peak shaving regulation, and promote the system flexibility by energy storage techniques. This work supports the technological development and breakthrough of the energy internet park.

Research on power quality assessment based on ubiquitous power IoT

Abstract With the rapid development of the Internet in this era, the traditional power grid is no longer able to meet the growing demand of the people for electricity. In order to realize a new generation of power system with comprehensive sensing, reliable transmission, intelligent processing and interconnection, the State Grid proposes the strategic goal of developing ubiquitous power IoT. Firstly, the concept and basic architecture of ubiquitous power IoT are elaborated, and then the main key technologies of the architecture of power energy consumption monitoring and management system are explained. The power quality parameters are measured and calculated, and the G1 method, which is computationally small and does not require consistency testing, is used to determine the subjective weights in the power quality evaluation process, which can truly reflect the power quality level of power grids in different regions. The information entropy method is used to determine the objective weights in the process of power quality evaluation to solve the error of artificially determined weights, and the combination of subjective weights and objective weights can more truly reflect the influence of each index on the comprehensive level of power quality. The results of the study show that PV is rated between 2 and 3 good when grid-connected and off-grid, and wind turbines are rated between 3 and 4 medium when grid-connected and off-grid. The results of the integrated assessment levels are in line with the actual situation and can meet the growing demand for electricity.

An attention-based wide and deep CNN with dilated convolutions for detecting electricity theft considering imbalanced data

• There is a serious sample imbalance in the data, which easily leads to a severe bias in the classification model, which in turn affects the classification accuracy. In order to solve the problem of sample imbalance, we proposed a method of using focal loss for model training to enhance the contribution of a small number of samples to model optimization. • Electricity consumption data is correlated in the time dimension. It is necessary to capture a larger receptive field to obtain global information and improve the model's accuracy. Keeping this concern in mind, we used dilated convolution to enlarge the receptive field without loss of information so that each convolution output contains a larger range of information, thereby capturing a larger receptive field and obtaining global information of the input data. • How to effectively integrate the feature expressions obtained by wide CNN and deep CNN is a key factor to improve the performance of the model. To address this problem, we adopt the channel-dimensional adaptive attention module to adaptively fuse the feature expressions obtained by wide CNN and deep CNN to improve the accuracy of model training. For the increasingly serious phenomenon of electricity theft, many researchers are trying to detect it. Traditional detection methods rely on physical inspection, which has low detection efficiency and high cost. However, the rapid application of advanced metering infrastructure (AMI) makes it possible to detect electricity theft via smart meters. In this work, we propose a hybrid improved wide and deep convolutional neural networks (CNN) method to address electricity theft detection on an imbalanced realistic dataset that presents a daily electricity consumption provided by State Grid Corporation of China. Our key contribution is the introduction of a channel-dimensional adaptive attention module concatenated with dilated convolutions. Moreover, we propose focal loss to solve the data imbalance problem. Experimental results demonstrate that compared to other state-of-the-art deep learning classifiers, our improved method has better performance (with 97.08% of MAP@100 and 83.61% of AUC), which verifies the effectiveness of the proposed method.

Key issues of Development and Utilization of New Energy in China under Carbon Peaking and Carbon Neutrality

High-quality development of new energy cannot be achieved without high-level utilization. Utilization rate has become a barometer to measure the effectiveness of new energy management. Through the joint efforts of government departments, power generation enterprises, power grid enterprises, and industry insiders and outsiders, new energy utilization rate has remained above 95% for many years, achieving high-level utilization during large-scale development. In the future, with the continuous increase in the penetration rate of new energy, maintaining high utilization rates presents significant challenges in terms of technology and cost. This paper utilizes the NEOS software independently developed by the State Grid Energy Research Institute to analyse the utilization of new energy in the future and proposes relevant policy recommendations for reasonable utilization rates.

Resolving Power Equipment Data Inconsistency via Heterogeneous Network Alignment

This paper studies the problem of resolving data inconsistency from multiple sources in managing data related to power equipment for China’s state grid corporation. This paper proposes to automatically align inconsistent devices from multiple sources, i.e., the same devices that have multiple entries with different values in each source, by HENGE, a HEtetrogeneous Network GEneration model. HENGE builds multiple data sources into a heterogeneous graph, and captures complex physical and semantic relationships among devices. HENGE combines both feature and relational information and improves alignment accuracy by feature-enhanced residual graph encoder and disentangled representation learning. HENGE is capable to learn from a small amount of labeled data, through a uniformity autoencoder trained on an unsupervised generation task. Experiments on two real-world datasets demonstrate the capability of HENGE in resolving inconsistent device entries in multiple sources.

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Incipient fault detection in power distribution systems is crucial to improve the reliability of the grid. However, the non-stationary nature and the inadequacy of the training dataset due to the self-recovery of the incipient fault signal, make the incipient fault detection in power distribution systems a great challenge. In this paper, we focus on incipient fault detection in power distribution systems and address the above challenges. In particular, we propose an ADaptive Time-Frequency Memory (AD-TFM) cell by embedding wavelet transform into the Long Short-Term Memory (LSTM), to extract features in time and frequency domain from the non-stationary incipient fault signals. We make scale parameters and translation parameters of wavelet transform learnable to adapt to the dynamic input signals. Based on the stacked AD-TFM cells, we design a recurrent neural network with ATtention mechanism, named AD-TFM-AT model, to detect incipient fault with multi-resolution and multi-dimension analysis. In addition, we propose two data augmentation methods, namely phase switching and temporal sliding, to effectively enlarge the training datasets. Experimental results on two open datasets show that our proposed AD-TFM-AT model and data augmentation methods achieve state-of-the-art (SOTA) performance of incipient fault detection in power distribution system. We also disclose one used dataset logged at State Grid Corporation of China to facilitate future research.

A space variable-scale scheduling method for digital vehicle-to-grid platform under distributed electric energy storage

With the widespread application of digital technology in the intelligent transportation field, the vehicle-to-grid (V2G) pattern, which utilizes electric vehicles (EVs) as the distributed storage resources of electric energy, has won increasingly more attention from authorities and decision-makers to promote the sustainable development of regenerative clean energy. This paper aims to study the interaction and integration problem between EVs and grid for the digital V2G platform, so as to support load aggregators making scheduling decisions. According to the variable-scale data analysis theory, a space–time scale space model is established to describe the demand response behavioral feature of EV users, and the lightning-Scale Transformation method (LST) is also proposed. Compared to the original unidirectional scale transformation modes, the LST is capable of adjusting the space and time observation scale collaboratively. A vehicle-to-grid scheduling method based on the lightning-Scale Transformation (V2G-LST) is put forward, in order to make scheduling plans by considering EV users’ behavioral feature and charger resource constraints. We collect the real dataset from 863 Beijing charging stations using the APIs of Amap, as well as the investigation data of the State Grid Corporation of China to verify the efficacy of our proposed method. Comparative experimental results verify that the V2G-LST could obtain the lower dispatch cost and higher EV charger usage rate than the maximum dispatchable quantity first method EVC-MDQ under both charging and discharging scenarios.

Mathematical methods for maintenance and operation cost prediction based on transfer learning in State Grid

Mathematical methods for maintenance and operation cost prediction based on transfer learning in State Grid

Design and Implementation of Microservice Secure Communication Framework based on National Secret Algorithm and Dynamic Key

With the acceleration of the pace of the national electricity reform and the wide application of the micro-service architecture, various network threats in the field of information security are increasing, and the power industry has become the “hardest hit area” for cyber attacks. In order to improve the safe implementation of the National Power Grid’s electronic projects and effectively resist the “malicious exploration” of various network threats, this paper proposes a microservice secure communication framework based on the combination of dynamic keys and national secret algorithms for a high concurrency web system based on microservices. The framework uses the national secret SM2 algorithm to generate session-level paired keys and then generates a digital signature through the SM3 algorithm, which effectively guarantees the integrity of the communication. Finally, it extracts the encryption key and encryption offset from the paired keys and uses the SM4 algorithm to encrypt the original request text payload. Timestamps and random numbers are added to each request to prevent tampering and replay attacks effectively. The system framework has been practically applied on the State Grid’s digital capability open platform, which ensures the security of micro-service communication and the safety and efficient transmission of data.

Research on intelligent storage system for DC control and protection system card based on FERET and RFID

In view of the current state grid company’s board card spare parts are in a state of extensive management, no hierarchical and classified management, and problems such as affecting the performance indicators and circulation of the DC control and protection system boards. In this paper, a special intelligent storage system for DC control and protection system based on face recognition technology (FERET) and radio frequency identification technology (RFID) is studied. Firstly, analyzing the technical principle of the intelligent storage system. Secondly, the warehouse in/out management module based on FERET and the automatic card warehouse in/out module based on RFID are designed. Then, the structural framework and workflow of the intelligent warehousing system are established. Finally, a special intelligent storage system for DC control and protection system card is designed, which has the characteristics of leading technology, stable performance, reliable quality, simplicity, and practicality.

Reactive Power Compensation Configuration of Offshore Wind Power Based on Economic Differential Pressure Theory

The conventional reactive power balance analysis method for offshore wind power transmission projects can be used to obtain many feasible solutions for reactive power compensation configuration, which requires a large number of simulation calculations to eliminate unreasonable schemes. The work is tedious and lacks theoretical guidance. In this paper, the main influencing factors, such as the current carrying capacity of offshore wind power and submarine cable, the mode of real-time power generation, and the reactive power output regulation of the wind turbine itself, are considered. The reactive power balance of offshore wind power transmission projects is derived. Combined with the economic differential pressure theory, the sea-side and land-side configuration methods of high reactance and dynamic reactive power compensation are put forward. On the basis of realizing real-time reactive power balance, the recommended reactive power compensation configuration scheme effectively reduces the active power loss of the transmission project, and at the same time, lowers the bus voltage of each node at sea, thus reducing the high risk of the excessive voltage of offshore wind farm. This project is supported by the Science and Technology Project of State Grid Corporation of China under “Research on multiple temporal and spatial coordinated optimal control theory for medium and long-distance large-scale offshore wind power transmission system” (No. 5100-202155305A-0-0-00).

Design of Backup Protective Hardware for Suspension Clamp of Electric Power Overhead Ground Wire

Aiming at the disconnection problem of power overhead ground wire caused by wind vibration or the action of power frequency short-circuit current, the newly revised “Eighteen major anti-accident measures of State Grid Corporation China” proposes that independent double string structure should be adopted in suspension clamp of overhead ground wire. Based on this, a research scheme of backup protective hardware for the suspension clamp of the overhead ground wire of the power transmission line is proposed. In this scheme, the backup protective hardware for the suspension clamp is designed and added on the premise that the original overhead ground wire-suspension clamp structure is not changed. It provides backup measures for the original suspension clamp and reduces suspension clamp heating by an electrical shunt. Finally, the mechanical failure load test and salt spray test are performed on the designed production. The results show that the designed production meets the standard and could be used in actual engineering. At the same time, the practical engineering application shows that the backup protective hardware can effectively reinforce the ground wire suspension clamp with double strings, avoiding the problem of dropping and breaking after the original clamp is broken.

Research on Non-Contact Electricity Inspection Technology of Unmanned Aerial Vehicles

The airborne non-contact electroscope developed in this paper does not need to touch the tower and can be remotely controlled to complete the electroscope. It can be widely used in the maintenance operation of various voltage levels, and the entire operation process is in line with the State Grid Corporation of China Electric Power Safe work regulations (power line part) regulations. The application of the device can effectively reduce the labor intensity of the operators, improve the operation efficiency, and ensure the safety of the operation.

Construction and intelligent analysis of power grid physical data knowledge graph based on Internet of Things for power system

Abstract The State Grid Corporation of China proposed the idea of building a ubiquitous power Internet of Things, which intends to endow the power system with adjustable perceptivity through the Internet of Things technology. Aiming at the power system under the Internet of Things, this article propounds a framework for the construction and intelligent assessment of the knowledge graph (KG). First of all, the introduction of the power Internet of Things system architecture and data life cycle will be introduced from the aspects of organisational structure, management system, team building, technical support and data security protection. Then, the key information is mined from the complicated physical text data of the power grid by using NLP technology. At the same time, a hybrid model is propounded for named entity recognition, which effectively uses context information to meliorate the accuracy of extraction. The experimental results evince that the accuracy rate of the Internet-based grid physical data KG construction and intelligent analysis framework proposed in article reaches 96.53%. It is a new guidance for the research and evolution of future power grid objects.

Predictive Data Analytics for Electricity Fraud Detection Using Tuned CNN Ensembler in Smart Grid

In the smart grid (SG), user consumption data are increasing very rapidly. Some users consume electricity legally, while others steal it. Electricity theft causes significant damage to power grids, affects power supply efficiency, and reduces utility revenues. This study helps utilities reduce the problems of electricity theft, inefficient electricity monitoring, and abnormal electricity consumption in smart grids. To this end, an electricity theft dataset from the state grid corporation of China (SGCC) is employed and this study develops a novel model, a mixture of convolutional neural network and gated recurrent unit (CNN-GRU), for automatic power theft detection. Moreover, the hyperparameters of the proposed model are tuned using a meta-heuristic method, the cuckoo search (CS) algorithm. The class imbalance problem is solved using the synthetic minority oversampling technique (SMOTE). The clean data are trained and then tested with the proposed classification. Extensive simulations are performed based on real energy consumption data. The simulated results show that the proposed theft detection model (CNN-GRU-CS) solved the theft classification problem better than other approaches in terms of effectiveness and accuracy by 10% on average. The calculated accuracy of the proposed method is 92% and the precision is 94%.

Research on Capital Operation Capability Evaluation of Energy State-owned Enterprises Based on Analytic Hierarchy Process

Improving the capital operation capacity of state-owned enterprises is an important goal of the reform of the state-owned capital authorized operation system. In the field of energy, reforming and improving the capital operation capacity of energy state-owned enterprises can effectively promote energy transformation. This paper uses the capital operation capability evaluation model constructed based on AHP to find that the capital operation capability of five typical energy central enterprises presents the results of “National Energy Group> PetroChina Group> State Grid Corporation> State Power Investment Corporation> China Southern Power Grid Corporatio”, which are all lower than the benchmark enterprise China Resources, but The average level is roughly comparable to that of China's new country.

Closed-form solution to the dynamic programming for a heavy-duty parallel hybrid vehicle energy management

Dynamic programming (DP) is frequently used to obtain the optimal solution to the hybrid electric vehicle (HEV) energy management. The trade-off between the accuracy and the computational effort is the biggest problem for the DP method. The closed-form solution to the DP is proposed to solve this problem. Firstly, the affine linear model of the engine fuel rate is obtained based on engine test data. The piecewise linear approximation of the motor power demand is obtained considering the different energy flows in the charging and discharging stages of the battery. Then, the second-order Taylor expansion for the cost matrix at each time and state grid point is introduced to get the closed-form solution of the optimal torque split. The results show that this method can greatly reduce the computing burden by 93% while ensuring near-optimal fuel economy compared with the conventional DP method.