Considering the volatility and randomness of wind speed, this research suggests an improved hunter-prey optimization (IHPO) algorithm-based extreme learning machine (ELM) short-term wind power prediction model to increase short-term wind power prediction accuracy. The original wind power history data from the wind farm are used in the model to achieve feature extraction and data dimensionality reduction, using the partial least squares’ variable importance of projection (PLS-VIP) and normalized mutual information (NMI) methods. Adaptive inertia weights are added to the HPO algorithm’s optimization search process to speed up the algorithm’s convergence. At the same time, the initialized population is modified, to improve the algorithm’s ability to perform global searches. To accomplish accurate wind power prediction, the enhanced algorithm’s optimal parameters optimize the extreme learning machine’s weights and threshold. The findings demonstrate that the method accurately predicts wind output and can be confirmed using measured data from a wind turbine in Inner Mongolia, China.

The insufficient amount of sample data and the uneven distribution of the collected data across faults are key factors limiting the application of machine learning in power transformer fault warning, as demonstrated by the poor adaptability of the established data-driven models under actual operating conditions. In this paper, an unsupervised and supervised learning method is designed for power transformer fault early warning based on electrical quantities and vibration signals. The method is based on the Fourier levels of transformer vibration signals under different electrical conditions measured in the field, and the vibration features are clustered according to their intrinsic properties by means of a spectral clustering algorithm. A decision tree model of the vibration characteristics under each cluster is then constructed to calculate early warning values for the transformer vibration spectrum under different electrical conditions, enabling the assessment of transformer production variability. The above process, which is based on field measurement data and data mining analysis methods, is cheaper than the existing transformer fault warning techniques at home and abroad and makes better use of information and training models.

A running transformer frequently experiences interturn faults; they are typically difficult to detect in their early stages but eventually progress to interturn short circuits, which cause damage to the transformer. Therefore, finding out the fault mechanism of the full interturn fault process can provide a theoretical basis for transformer fault detection. In this paper, an electromagnetic-solid mechanics coupled finite element model consistent with an actual oil-immersed three-phase transformer is established. The transient process of winding from interturn discharge to interturn short circuit is simulated to study the electromagnetic characteristics as well as the mechanical characteristics during transformer failure. The model parameters of the transformer are simulated to obtain the fault current, electromagnetic parameters and other performance parameters to study the characteristics of the magnetic field and coil force when interturn faults occur. Finally, the vibration of the transformer casing is used to detect as well as diagnose the transformer fault situation, providing a theoretical basis for the study of transformer detection and diagnosis capability improvement measures.

The remaining useful life (RUL) of lithium-ion batteries (LIBs) needs to be accurately predicted to enhance equipment safety and battery management system design. Currently, a single machine learning approach (including an improved machine learning approach) has poor generalization performance due to stochasticity, and the combined prediction approach lacks sufficient theoretical support at the same time. In this paper, we first analyze the prediction principles and applicability of models such as long and short-term memory networks and random forests, and then propose a method for predicting the RUL of batteries based on the integration of multiple-model, and finally validate the proposed model by using experimental data. The experimental results show that (1) for the proposed model, in the best case, the root-mean-square error (RMSE) does not exceed 0.14%, which has a stronger generalization; (2) for the comparison with the single model used, the average RMSE is reduced by 46.2%, 43.7%, and 80.6%, which has a better fitting performance. These results show that the model has good prediction accuracy and application prospects for predicting the RUL of energy storage batteries.

With the deepening reform of the power system, power sales companies need to adopt new power sales strategies to provide customers with better economic marketing solutions. Customer-side configuration of an energy storage system (ESS) can participate in power-related policies to reduce the comprehensive cost of electricity for commercial and industrial customers and improve customer revenue. For power sales companies, this can also attract new customers, expand sales and quickly capture the market. However, most of the ESS evaluation models studied so far are based on historical data configuration of typical daily storage capacity and charging and discharging scheduling instructions. In addition, most models do not adequately consider the performance characteristics of the ESS and cannot accurately assess the economics of the energy storage model. This study proposes an intelligent power sales strategy based on load forecasting with the participation of optimal allocation of ESS. Based on long short-term memory (LSTM) artificial neural network for predictive analysis of customer load, we evaluate the economics of adding energy storage to customers. Based on the premise of the two-part tariff, the ESS evaluation model is constructed with the objective of minimizing the annual comprehensive cost to the user by considering the energy tariff and the savings benefits of the basic tariff, assessing the annualized cost of ESS over its entire life cycle, and the impact of battery capacity decay on economics. The particle swarm optimization (PSO) algorithm is introduced to solve the model. By simulating the arithmetic example for real customers, their integrated electricity costs are significantly reduced. Moreover, this smart power sales strategy can provide different sales strategies according to the expected payback period of customers. This smart sales strategy can output more accurate declared maximum demand values than other traditional sales strategies, providing a more economical solution for customers.

The issues of low accuracy, poor generality, high cost of transformer fault early warning, and the subjective nature of empirical judgments made by field maintenance personnel are difficult to solve with the traditional measurement methods used during the development of the transformer. To construct a transformer fault early warning analysis, this study recommends a data-fusion-based decision tree approach for merging electrical quantity signals with a non-electrical amount of vibration signals. By merging a decision tree inference with actual operation data, a clustering center, and an early warning model, this method creates a transformer fault early warning model with self-learning ability and adaptive capabilities. After reasonable verification, the method becomes more universal and interpretable, and it can successfully conduct an early warning of transformer faults.