Search

Accurate differentiation of energy consumption information of residential users is of great significance for load planning, scheduling, operation and management of power system, and is the basic premise for realizing intelligent perception of energy system and energy saving and carbon reduction. Considering that the conventional single-layer clustering method has limited clustering stability and clustering effect, this paper takes the key family feature factors as the modified feature quantity of quadratic clustering, and proposes a study of user energy characteristics based on double-layer clustering and modification. Firstly, the user’s energy consumption data is collected and pre-processed, and the user’s energy consumption curve is clustered and analyzed by using the integrated clustering algorithm based on voting and the advantages of each member algorithm. Then, the key family characteristic factors are obtained, and the results of one-layer clustering and key family characteristic factors are combined to carry out two-layer clustering of the same category of users in the form of questionnaire survey. Finally, the nonlinear mapping capability of Support Vector Machine (SVM) is used to reverse correct the results of the one-layer clustering. The actual algorithm data of the residents’ demand response experiment in a southeastern province are compared. The results show that compared with the single-layer clustering algorithm, the proposed method can accurately distinguish the energy consumption characteristics and adjustable potential of different users, and correct the wrong clustering results in the single-layer clustering. The clustering stability and clustering effect have been effectively improved.The example results show that the clustering results modified by SVM can better mine and distinguish user energy characteristics, and can be used to solve the problem of the current demand response clustering algorithm not being able to comprehensively and objectively describe the participation willingness and response-ability of residential users in the implementation process. It can also provide a basis for peak shaving and power grid frequency regulation.

With the expansion of the scale of wind power integration, the safe operation of the grid is challenged. At present, the research mainly focuses on the prediction of a single wind farm, lacking coordinated control of the cluster, and there is a large prediction error in transitional weather. In view of the above problems, this study proposes an adaptive wind farm cluster prediction model based on transitional weather classification, aiming to improve the prediction accuracy of the cluster under transitional weather conditions. First, the reference wind farm is selected, and then the improved snake algorithm is used to optimize the extreme gradient boosting tree (CBAMSO-XGB) to divide the transitional weather, and the sensitive meteorological factors under typical transitional weather conditions are optimized. A convolutional neural network (CNN) with a multi-layer spatial pyramid pooling (SPP) structure is utilized to extract variable dimensional features. Finally, the attention (ATT) mechanism is used to redistribute the weight of the long and short term memory (LSTM) network output to obtain the predicted value, and the cluster wind power prediction value is obtained by upscaling it. The results show that the classification accuracy of the CBAMSO-XGB algorithm in the transitional weather of the two test periods is 99.5833% and 95.4167%, respectively, which is higher than the snake optimization (SO) before the improvement and the other two algorithms; compared to the CNN–LSTM model, the mean absolute error (MAE) of the adaptive prediction model is decreased by approximately 42.49%–72.91% under various transitional weather conditions. The relative root mean square error (RMSE) of the cluster is lower than that of each reference wind farm and the prediction method without upscaling. The results show that the method proposed in this paper effectively improves the prediction accuracy of wind farm clusters during transitional weather.

With the increasing demand for reliable power supply and the widespread integration of distributed energy sources, the topology of distribution networks is subject to frequent changes. Consequently, the dynamic alterations in the connection relationships between distribution transformers and feeders occur frequently, and these changes are not accurately monitored by grid companies in real-time. In this paper, we present a data-driven machine learning approach for identifying the feeder-transformer relationship in distribution networks. Initially, we preprocess the collected three-phase voltage magnitude data of distribution transformers, addressing data quality and enhancing usability through three-phase voltage normalization. Subsequently, we derive the correlation coefficient calculations between distribution transformers, as well as between distribution transformers and feeders. To tackle the challenging task of determining the correlation coefficient threshold, we propose a multi-feature fusion approach. We extracted additional features from the feeders and combined them with the correlation coefficients to create a feature matrix. Machine learning algorithms were then applied to calculate the results. Through experimentation on a real distribution network in Jiangxi province, we demonstrated the effectiveness of the proposed method. When compared to other approaches, our method achieved outstanding results with an F1 score of 0.977, indicating high precision and recall. The precision value was 0.973 and the recall value was 0.981. Importantly, our method eliminates the need for additional measurement installations, as the required data can be obtained using existing collection devices. This significantly reduces the application cost associated with implementing our approach.

In a modern power system, to realize the safe operation of units and maintain the frequency stability of the power network, various means of frequency modulation can be adopted. However, there are some deficiencies in the real-time monitoring and assessment management of primary frequency modulation (PFM). To solve these problems, a PFM online monitoring and management method based on the “master–sub” control station model in a wide area measurement system (WAMS) is proposed as a control strategy to support frequency modulation of units and assist power network assessment. In the hybrid monitoring system strategy of the master control station and sub control station, the sub control station is built locally in the power plant to monitor the operational status of the unit in real-time and calculate the PFM assessment index. The master control station is built in the dispatching center, receiving the assessment data uploaded by the sub control station and sending the PFM simulation test instruction. This strategy can effectively improve the real-time performance of dynamic monitoring and parameter calculation, and reduce the probability of frame loss and communication instability in long-distance data transmission. The experimental results show that the PFM online monitoring management control strategy based on the “master–sub” control station model can effectively monitor the unit and provide data support for PFM assessment.