Abstract:New energy field station does not have the mechanical inertia of the traditional rotary generator, so it is difficult to support the system frequency change. With the continuous improvement of the proportion of new energy power generation, if the new energy field station does not participate in the system frequency adjustment, the frequency will change rapidly when the system fluctuates, which will further deteriorate the system frequency stability, so it is of great significance to study the frequency regulation technology characteristics of the new energy field station. At the same time, as a key link in the new energy grid-connected control system, the phase-locked loop has the function of tracking the frequency signal of the grid connection point, and can help analyze the characteristics of voltage and current. In order to accelerate the speed of the frequency response and adjustment of the new energy station, a third- order phase-locked loop with faster frequency response is designed in this article, which also shares better steadystate performance and dynamic performance in view of the commonly used second-order phase-locked loop that does not have zero steady-state error when the frequency ramp changes, and is applied to the semi- physical simulation platform of the new energy field station. By simulating the step changes of different frequencies and the changes of different frequency ramps, the grid-connected frequency modulation technology of new energy field stations is verified.

Abstract:With the increase of urban electricity consumption and the popularity of new- type loads, the problem of urban grid blockage demands prompt solution. As a new type of load with high power consumption, wide distribution range and strong regulation potential in urban power grids, 5G base stations can effectively alleviate the blockage of urban medium voltage distribution grids by participating in demand response. Therefore, blockage control model of urban medium voltage distribution network considering communication base station demand response is constructed. Firstly,by analyzing the working principle of 5G base station equipment, a power tunable model for 5G base stations is established. Then, a blockage control model for the urban medium voltage distribution network is established, with the objective of minimizing the block-age control cost while taking into account the network trend constraint and the communication constraint of 5G base stations. Finally, the proposed model is verified through an example analysis, which shows that the economic efficiency can be effectively improved while solving the blockage problem of the urban medium voltage distribution network.

Abstract:In order to encourage users to implement friendly interaction with the power grid and reduce energy consumption and power load, the way to equitably share the interactive benefits of the power grid company to all participating users according to a certain subsidy proportion is studied. In order to solve the combination explosion problem of the traditional Shapley value method, a compensation method for sharing the interactive benefits of users based on the Shapley value sampling estimation is proposed. Under the constraint of meeting the balance of payments, the method can reduce sample size by stratified random sampling. In order to fix the sample allocation amount of each layer, the advantages and disadvantages of random allocation method, average allocation method and Neyman optimal allocation method are comprehensively compared. In order to solve the problem that the standard deviation of samples at each layer of participants is unknown in Neyman optimal allocation method, an iterative ε(t) estimation optimal allocation method based on reinforcement learning algorithm is proposed. Numerical examples show that the proposed method has all the characteristics of Shapley value method, can accurately estimate the allocation results of Shapley value method, and can achieve fair and reasonable allocation, while effectively reducing the calculation time.

Abstract:Parks are the main source of urban carbon emissions in China. To clarify the composition of park- level carbon emission sources or sinks is the key to carrying out research on lowcarbon pathways for parks. At present, there are no park-level carbon emission calculation-related norms or guidelines at home and abroad. Most of the research that has been carried out is to calculate and analyze the carbon emissions of a specific type of stock park, without fully considering the data availability of new parks or the adaptability of the calculation system to different types of parks. Therefore, a park-level carbon emission calculation method considering the characteristics of various types of parks is proposed. The calculation system is constructed from five dimensions,including energy activities (covering agriculture, industry, construction, transportation, tourism facilities, power infrastructure, etc.),agricultural production, industrial production, waste treatment,green plant carbon sinks. The calculation formulas for both complete data scenario and missing data scenario are respectively proposed as well. Case study shows that the proposed method is applicable to the calculation of total carbon emissions and structural analysis of various types of parks such as agricultural parks, industrial manufacturing parks, business parks, and tourism parks.

Abstract:Under the background of domestic double carbon target, low-carbon energy use and energy revolution is extremely urgent. In order to meet the requirements of economy and low carbon,bidding game between the community comprehensive energy generators and users is considered and ladder-type carbon trading is added. Firstly, ladder-type carbon trading and the stackelberg game are introduced. Then, Stackelberg game model under the ladder-type carbon trading is established. Finally, the model is solved by using CPLEX solver and particle swarm optimization algorithm through practical examples. It’s verified that ladder-type carbon trading in the stackelberg game model can effectively reduce carbon emissions. The above research provides reference for the low-carbon economic operation of power generators and users.

Abstract:In the islanded microgrid with a high proportion of new energy, the intermittency and volatility of wind power will increase the uncertainty of the operation and dispatching of the microgrid, which may affect the safety and stablility of the system operation in serious cases. Therefore, an operation strategy of offshore island microgrid considering demand side management of user comfort is proposed. Firstly, the fine modeling and differentiated demand response strategies are carried out for different types of load users in the microgrid, and the evaluation indexes of different types of users are proposed. Then, the day-ahead scheduling framework is established to optimize the user comfort and minimize the daily operation cost of the microgrid, and the day-ahead scheduling plan is obtained by using yalmip+cplex solver. Finally, an offshore island microgrid is taken as an example to verify the effectiveness and universality of the proposed strategy in different wind power scenarios.

Abstract:Short-term forecasting of power load can reasonably determine the operation mode of unit, arrange the daily dispatching plan, improve the measurement accuracy, which is of great significance to realize the power balance and ensure the safe and economic operation of the system. When using neural network to predict load in short-term, the learning ability of the model will be greatly reduced if the training data is insufficient. At the same time, due to the characteristics of hourly cycle, daily cycle, weekly cycle and seasonal cycle of power load data, the conventional neural network training model can not reflect the different cycle characteristics of load, which will also have a certain impact on the accuracy of prediction results. Therefore, a data enhancement method is proposed to effectively solve the problem of insufficient training data in power load forecasting. Secondly, according to the periodic characteristics of load, a fusion scheme of parallel sequential convolutional neural network model with different periodic features is furtherly proposed, which effectively reflects the multi-periodic characteristics of load data, and thus improves the accuracy of short- term prediction of power load. Through the modeling and training of load data in a certain city, the effectiveness and superiority of the proposed method in short-term forecasting are verified.

Abstract:PV penetration is steadily increasing with the large-scale utilization of new energy sources. Accurate PV power prediction can bring more benefits to grid enterprises. Based on this, a random forest prediction model with multi-feature analysis extraction is proposed for ultra-short- term PV power prediction.Firstly, the collected PV data is pre-processed to clean up the missing and duplicate values. Then, correlation analysis is performed on the influencing factors and factors with strong correlation are selected. Next, feature engineering is performed on the screened factors and the processed feature vector is used as input of the prediction model. Finally, the random forest prediction model is built and compared with BP, RBF and MLP models. Empirical results show that the model proposed has better fit and higher prediction accuracy, which is of certain guidance for PV prediction work.

Abstract:It is an economic and practical method to provide demand response resources by using the coupled thermal inertia of heating, ventilation and air conditioning systems（HVAC）and buildings. Buildings with active energy storage systems have greater potential to reduce electrical load during demand response. A simulation platform is built and its accuracy is verified, the research is carried out from two aspects：passive energy storage of buildings and air-conditioning and active energy storage of heat storage tank. The flexible combination of three strategies of precooling, temperature reset and shutdown of refrigeration unit is adopted to analyze the demand response potential of buildings, air- conditioning and heat storage tank. The results show that this strategy can meet both short-term（0.5 h）and long-term（2.5 h）demand response. For short-term demand response plans, the thermal inertia of building and air-conditioning system can be used. For long-term demand response plan, active energy storage technology is needed to meet indoor thermal comfort requirements.

Abstract:Short-term load forecasting plays an important role in power system planning and operation. A hybrid short-term load probability density forecasting method based on convolutional bi-directional long short-term memory quantile regression blending attention mechanism is proposed. Firstly, the weather variables and historical loads are selected by using relevant mechanisms.Next, the Copula model is used to calculate the risk threshold,which is used to construct the peak binary indicator input characteristics. Then, the selected feature sets are input into the convolutional bi-directional long short-term memory quantile regression blending attention mechanism prediction model. Then, kernel density estimation is used to fit the load probabilistic prediction. Finally, the prediction performance is evaluated using the mean absolute percentage error and root mean square error. The simulation results show that proposed model has higher prediction accuracy.

Abstract:Provinces of sending- end grids not only need to balance its internal high growth load and new energy resources, but also meet the demand for the external transmission. Therefore, the lack of adjustment ability of the electricity exporting regions challenges the operation economy and stability. Demand response is an important technology to provide more regulation ability for power systems, which can effectively minor the peak- valley difference and relieve the tension of the power supply. At present, demand response in China has been carried out in many electricity importing regions, but the electricity exporting regions carrying out demand response are still few. Aiming at the above problems, the necessity of demand response in electricity exporting regions is analyzed from four aspects：rapid load growth, a high proportion of new energy generation, the risk of power supply shortage, and inter-provincial power transmission and trading. Suggestions are put forward from three aspects：development path of market supporting mechanism, demand response scheme considering regional characteristics, and emergency demand response planning, which can provide advice and guidance for the development of demand response in electricity exporting regions.

Abstract:Aiming at the difficulty for a large group of comprehensive energy users to choose when purchasing energy service packages, a comprehensive energy package recommendation method based on user feature clustering is proposed to improve user stickiness. First of all, the comprehensive energy user information collected is constructed by knowledge graph, the missing user information is supplemented and improved, and the relationship between users is analyzed. Then, spectral clustering method is used to cluster the constructed user knowledge map, calculate the similarity among users, and extract the interest features representing the diversity of energy use behavior of comprehensive energy users. Finally, the random forest model is used to calculate the predicted scores of comprehensive energy users for each energy service package. After sorting the predicted scores, the part of the package with the highest score is selected to present the package service content for users through the online platform, so as to achieve accurate recommendation for users. By comparing the package recommendation model proposed in this paper with the traditional recommendation model, the results show that the integrated energy package recommendation method based on user feature clustering can achieve effective user precision energy service recommendation for integrated energy service companies, which is conducive to improving the market competitiveness of energy service companies, and provides technical support for the transformation of power enterprises into integrated energy service providers.

Abstract:Non technical losses in power systems, represented by abnormal electricity consumption by power users, will typically result in significant increase in the operating costs of power supply companies. Firstly, deep neural detection method for abnormal electricity consumption by power users is proposed. Based on the characteristics of electricity consumption by power users, a deep confidence network（DBN）is used to extract features from the original electricity load data and obtain corresponding features.Then, feature classification is completed using an extreme learning machine（ELM）, thus establishing a basic model for detecting abnormal electricity consumption by power users. Finally, an improved fruit fly optimization algorithm（IFOA）to optimize the network weights and inter layer bias parameters of DBN is proposed,thereby obtaining an abnormal electricity consumption detection model for power users based on IFOA-DBN-ELM. Experimental results show that compared with other detection methods, the accuracy, precision, and detection rate of the method proposed are significantly higher, and false detection rate are lower than other methods. It can accurately detect power users with abnormal electricity consumption behavior and help reduce the operating costs of power supply companies.

Abstract:Due to the high randomness and irregularity of residential users’electricity demand, detailed data analysis is urgently needed to define the behavior characteristics of users to provide more reasonable electricity suggestions and demand response potential. Based on the fine-grained electricity consumption data and user information of residents, a classification of electricity residential users based on multi- dimensional electricity consumption behavior data is proposed. First of all, the non-intrusive smart meter is used to obtain the fine-grained electricity consumption data of residents；Then the user’s electricity consumption behavior is analyzed, and electricity consumption characteristics are found. Then,the CRITIC weight method is used to adaptively configure the weights of each index, and through the evaluation indicators of 6 types of clusters, 4 kinds of clustering algorithms and 3 data distance calculations are compared to achieve the optimal clustering method and the choice of the number of clusters. The actual data of a residential area are used to verify the power consumption characteristics and the effectiveness of the weight-fixing clustering method proposed in this paper, and the residential user groups are divided into two categories with obvious differences in electricity consumption behavior.

Abstract:In order to effectively define the influencing factors of power outage events, improve the accuracy of emergency scenario dynamic deduction models, and avoid the occurrence of power emergencies, a large-scale power outage emergency scenario dynamic deduction model based on improved Bayesian networks is designed.Firstly, five network levels of initial scenario, triggering scenario,outbreak scenario, recovery scenario, and disappearance scenario are analyzed to construct a large-scale power outage scenario network. Then, emergency decision- making subject, object, target,plan, and decision- making environment are considered, the emergency decision-making process of large-scale power outage events is simulated, improved Bayesian networks is used to calculate the probability of movement between multi-level scenario networks, and the dynamic evolution law of events is determined. Finally, based on the input results of large-scale power outage event data, the dynamic inference path and optimal emergency plan including large-scale power outage events are obtained. The experimental results show that after applying the design model, the reduction rate of power outage area is 48.57% , and the actual power outage area of power outage events is significantly reduced. The dynamic deduction process of emergency scenarios has been improved, and the emergency response plan is matched with the actual power outage situation, which can efficiently respond to large-scale power outage events and has high application value.

Abstract:In view of the fact that a large number of data that are accurate to single household controllable load at this stage are mostly from abroad and are not suitable for domestic residents to participate in demand response, household controllable loads in a residential area in China by questionnaire survey is counted, and feasibility and potential for peak shaving and improving the consumption level of wind power and photovoltaic are analyzed. Firstly, based on the principle of being objective and easy to answer, the household controllable load questionnaire is designed, and 466 valid answers are collected after publication. Then the questionnaire survey data quality comprehensive evaluation system is used to evaluate the statistical questionnaire. Based on the evaluation results, Python is used to quantify the questionnaire information with good evaluation level and above, and the demand response potential of household controllable load is calculated by using the bottom-up hierarchical modeling idea and combining with the mathematical model of household controllable load. Finally, by comparing the demand response potential of various types of controllable loads of residents, it is known that household controllable loads in China can participate in demand response are air conditioning, electric water heaters, washing machines, etc. By comparing household controllable load curve with the typical output of wind power and photovoltaic power generation, it can be seen that household controllable load has the potential to improve the consumption level of photovoltaic power generation and wind power.

Abstract:As the key node connecting power generation side and user side, electricity selling enterprises are related to the stable operation of the power market. In the context of new electricity reform, many provinces in China have built credit management systems and achieved certain results. With continuous deepening of the reform of the power market, the current management system that relies on the combination of the simple credit evaluation and guarantee credit line can no longer fully adapt to the current market environment. Consequently, taking typical power market in China and the United States as examples, a multi-level analysis of electricity selling enterprises from the aspects of evaluation mode, third-party evaluation, guaranteed and unsecured credit line is proposed. Combined with the development needs of China’s electricity market, suggestions are put forward on the construction of credit management system for electricity selling enterprises from various aspects of construction of credit evaluation indicators, third- party evaluation, credit line and so on.