Evaluation of Multi-Temporal-Spatial Scale Adjustment Capability and Cluster Optimization Operation Method for Distribution Networks with Distributed Photovoltaics

Themassive integration of high-proportioned distributed photovoltaics into distribution networks poses significant challenges to the flexible regulation capabilities of distribution stations.To accurately assess the flexible regulation capabilities of distribution stations,amulti-temporal and spatial scale regulation capability assessment technique is proposed for distribution station areas with distributed photovoltaics,considering different geographical locations,coverage areas,and response capabilities.Firstly,the multi-temporal scale regulation characteristics and response capabilities of different regulation resources in distribution station areas are analyzed,and a resource regulation capability model is established to quantify the adjustable range of different regulation resources.On this basis,considering the limitations of line transmission capacity,a regulation capability assessment index for distribution stations is proposed to evaluate their regulation capabilities.Secondly,considering different geographical locations and coverage areas,a comprehensive performance index based on electrical distance modularity and active power balance is established,and a cluster division method based on genetic algorithms is proposed to fully leverage the coordination and complementarity among nodes and improve the active power matching degree within clusters.Simultaneously,an economic optimization model with the objective of minimizing the economic cost of the distribution station is established,comprehensively considering the safety constraints of the distribution network and the regulation constraints of resources.This model can provide scientific guidance for the economic dispatch of the distribution station area.Finally,case studies demonstrate that the proposed assessment and optimization methods effectively evaluate the regulation capabilities of distribution stations,facilitate the consumption of distributed photovoltaics,and enhance the economic efficiency of the distribution station area.

Integrated Generative Adversarial Network and XGBoost for Anomaly Processing of Massive Data Flow in Dispatch Automation Systems

Existing power anomaly detection is mainly based on a pattern matching algorithm.However,this method requires a lot of manual work,is time-consuming,and cannot detect unknown anomalies.Moreover,a large amount of labeled anomaly data is required in machine learning-based anomaly detection.Therefore,this paper proposes the application of a generative adversarial network(GAN)to massive data stream anomaly identification,diagnosis,and prediction in power dispatching automation systems.Firstly,to address the problem of the small amount of anomaly data,a GAN is used to obtain reliable labeled datasets for fault diagnosis model training based on a few labeled data points.Then,a two-step detection process is designed for the characteristics of grid anomalies,where the generated samples are first input to the XGBoost recognition system to identify the large class of anomalies in the first step.Thereafter,the data processed in the first step are input to the joint model of Convolutional Neural Networks(CNN)and Long short-term memory(LSTM)for fine-grained analysis to detect the small class of anomalies in the second step.Extensive experiments show that our work can reduce a lot of manual work and outperform the state-of-art anomalies classification algorithms for power dispatching data network.