Wind power has great uncertainty and short-term wind power forecasting technology can provide great help to power system scheduling after wind power integration. In this paper, a Convolutional neural network -bidirectional long and short-term memory network combination modeliCNN-BiLITMjbased on feature selection is proposed. Firstly, high correlation feature parameters were optimized based on effective feature screening of multidimensional feature datasets. Secondly, the input data are weighted according to the feature correlation to form a multi-dimensional feature data set. Finally, CNN-BiLSTM developed the wind energy forecast model. For verification, the KDD Cup 2022 wind power generation prediction data set was employed. The outcomes demonstrate that CNN-BiLSTM has a greater time series data utilization rate and prediction accuracy.

Motor-bearing fault diagnosis is critical for industrial equipment reliability, yet traditional data-driven methods require extensive labeled data, which are often scarce in real-world applications. To address this challenge, we propose a Transformer transfer learning network (TTLN) for accurate fault diagnosis under cross-condition scenarios, particularly when target domain data are limited. First, we develop a Transformer-based fault diagnosis model that captures long-range dependencies in sequential data through self-attention, achieving high accuracy under single operating conditions. Second, we introduce the TTLN framework, which integrates domain adaptation to align marginal and conditional distributions, enabling robust cross-condition fault diagnosis with minimal target domain samples. Finally, we validated the proposed method on the CWRU and PU datasets, demonstrating the TTLN’s superior performance in data-scarce scenarios. For example, the TTLN achieved over 95% accuracy with only 100 target samples, outperforming traditional methods and fine-tuning-based approaches. The results underscore the TTLN’s effectiveness in cross-condition fault diagnosis, offering a practical solution for industrial applications with limited labeled data.

With the advancement of power systems, the integration of a substantial portion of renewable energy often leads to frequent voltage surges and increased fluctuations in distribution networks (DNs), significantly affecting the safety of DNs. Active distribution networks (ADNs) can address voltage issues arising from a high proportion of renewable energy by regulating distributed controllable resources. However, the conventional mathematical optimization-based approach to voltage reactive power control has certain limitations. It heavily depends on precise DN parameters, and its online implementation requires iterative solutions, resulting in prolonged computation time. In this study, we propose a Volt-VAR control (VVC) framework in ADNs based on multi-agent reinforcement learning (MARL). To simplify the control of photovoltaic (PV) inverters, the ADNs are initially divided into several distributed autonomous sub-networks based on the electrical distance of reactive voltage sensitivity. Subsequently, the Multi-Agent Soft Actor-Critic (MASAC) algorithm is employed to address the partitioned cooperative voltage control problem. During online deployment, the agents execute distributed cooperative control based on local observations. Comparative tests involving various methods are conducted on IEEE 33-bus and IEEE 141-bus medium-voltage DNs. The results demonstrate the effectiveness and versatility of this method in managing voltage fluctuations and mitigating reactive power loss.

Scenario generation proves to be an effective approach for addressing uncertainties in stochastic programming for power systems with integrated renewable resources. In recent years, numerous studies have explored the application of deep generative models to scenario generation. Considering the challenge of characterizing renewable resource uncertainty, in this paper, we propose a novel two-stage generative architecture for renewable scenario generation using diffusion models. Specifically, in the first stage the temporal features of the renewable energy output are learned and encoded into the hidden space by means of a representational model with an encoder–decoder structure, which provides the inductive bias of the scenario for generation. In the second stage, the real distribution of vectors in the hidden space is learned based on the conditional diffusion model, and the generated scenario is obtained through decoder mapping. The case study demonstrates the effectiveness of this architecture in generating high-quality renewable scenarios. In comparison to advanced deep generative models, the proposed method exhibits superior performance in a comprehensive evaluation.