Power load forecasting (PLF) has a positive impact on the stability of power systems and can reduce the cost of power generation enterprises. To improve the forecasting accuracy, more information besides load data is necessary. In recent years, a novel privacy-preserving paradigm vertical federated learning (FL) has been applied to PLF to improve forecasting accuracy while keeping different organizations’ data locally. However, two problems are still not well solved in vertical FL. The first problem is a lack of a full data-processing procedure, and the second is a lack of enhanced privacy protection for data processing. To address it, according to the procedure in a practical scenario, we propose a vertical FL XGBoost-based PLF, where multiparty secure computation is used to enhance the privacy protection of FL. Concretely, we design a full data-processing PLF, including data cleaning, private set intersection, feature selection, federated XGBoost training, and inference. Furthermore, we further use RSA encryption in the private set intersection and Paillier homomorphic encryption in the training and inference phases. To validate the proposed method, we conducted experiments to compare centralized learning and vertical FL on several real-world datasets. The proposed method can also be directly applied to other practical vertical FL tasks.

No abstract

The distributed big data security risk control model achieves the control of big data security risk by distributed training of data feature vectors. The lack of processing of encrypted data leads to weak generalization ability. In this regard, a big data security risk control model based on federal learning algorithm is proposed. The heterogeneous data is formatted and the original data is preprocessed by data discretization and data scaling. The optimized federation learning algorithm is used to match the encrypted data, and the big data security risk control model is constructed to improve the generalization ability of the model. In the experiments, the proposed model is tested for its generalization ability. The analysis of the experimental results shows that the big data security risk control model constructed by using the proposed method has high data generalization ability.

With the construction of the modern power system, power load forecasting is significant to keep the electric Internet of Things in operation. However, it usually needs to collect massive power load data on the server and may face the problem of privacy leakage of raw data. Federated learning can enhance the privacy of the raw power load data of clients by frequently transmitting model updates. Concerning the increasing communication burden of resource-heterogeneous clients resulting from frequent communication with the server, a communication-efficient federated learning algorithm based on Compressed Model Updates and Lazy uploAd (CMULA-FL) was proposed to reduce the communication cost. CMULA-FL also integrates the error compensation strategy to improve the model utility. First, the compression operator is used to compress the transmitted model updates, of which large norms are uploaded to reduce the communication cost of each epoch and transmission frequency. Second, by measuring the error of compression and lazy upload, the error is accumulated to the next epoch to improve the model utility. Finally, based on simulation experiments on the benchmark power load data, the results show that the communication cost decreases at least 60% with controlled loss of model prediction compared with baseline. INDEX TERMS Power load forecasting, federated learning, quantization, lazy upload, error compensation.

In view of the increasing data volume and the increasingly difficult data analysis in the power industry, an intelligent and efficient analysis and mining framework for power big data is designed to quickly obtain valuable information. Analyze the overall framework of the power big data center, mainly including the service layer, verification layer, data source layer, and feature analysis layer. In addition, through analyzing the process of data mining, it is found that the business needs to be strengthened And realize expansion. The framework design of power big data intelligent analysis and mining technology mainly includes power market demand, customer analysis, high-performance data analysis, service system, data security governance and other modules. Through the analysis of an example of intelligent power big data mining, the analysis results show that the intelligent power data mining has good analysis effect and high mining accuracy.