In microgrids, energy storage systems (ESS) can mitigate the intermittency and uncertainty associated with large amounts of renewable energy connected to the grid. Cloud energy storage (CES) is a solution proposed by scholars over the last two years. It provides energy storage and trading services that can alleviate high investment costs and small‐scale wind and light abandonment problems. However, large‐scale energy mutualisation and fine scheduling of energy become significant challenges for further development. This study proposes a CES scheduling architecture based on multi‐microgrids. CES extends the scope of power trading from a single microgrid to multi‐microgrids, with the microgrid capable of interacting with neighbouring microgrids for power and reducing the transmission pressure on the larger grid. In addition, this study defines the game strategy for power trading between cloud storage operators, considering the reduction in electricity costs due to dishonest behaviour by users. The simulation results indicate that the proposed dispatching architecture and strategy can effectively improve the consumption rate of new energy sources, mitigate grid fluctuations, and further reduce electricity costs for users while also being resilient to dishonest user behaviour.

In the Internet era, network malicious intrusion behaviors occur frequently and network intrusion detection is increasingly in demand. Addressing the challenges of high-dimensional data, nonlinearity and noisy network traffic data in network intrusion detection, a net-work intrusion detection model is proposed in this paper. Firstly, a hybrid multi-model feature selection and kernel-based dimensionality reduction algorithm is proposed to map high-dimensional features to low-dimensional space to achieve feature dimensionality reduction and enhance nonlinear differentiability. Then the semantic feature mapping is introduced to convert the low-dimensional features into color images which represent distinct data characteristic. For classifying these images, an integrated convolutional neural network is constructed. Moreover, sub-model fine-tuning is performed through transfer learning and weights are assigned to improve the performance of multi-classification detection. Experiments on the UNSW-NB15 and CICIDS 2017 datasets show that the proposed model achieves accuracies of 99.99% and 99.96%. The F1-scores of 99.98% and 99.91% are achieved respectively.

The safe and reliable operation of the pitch system is essential for the stable and efficient operation of a wind turbine (WT). The pitch fault data collected by supervisory control and data acquisition systems (SCADA) often contain a wide variety of variables, leading to redundant features that interfere with the accuracy of final diagnosis results, making it difficult to meet requirements. Also, the problem of extracting only local features while ignoring global information is present in the feature extraction process using the deep Convolutional Neural Network (CNN) model. To address these issues, the global average correlation coefficient is proposed in this article to measure the correlation between multiple variables in SCADA data. By considering the correlation among multiple variables comprehensively, redundant features are effectively eliminated, enhancing the accuracy of fault diagnosis. Furthermore, a new local amplification fusion architecture network (LAFA-Net) based on multi-head attention (MHA) is introduced. An efficient local feature extraction module, designed to enhance the model’s perception of detailed features while maintaining global context information, is first introduced. LAFA-Net integrates the advantages of CNN and MHA, efficiently extracting and fusing valuable features from filtered data for both local and global aspects. Experiments on real pitch fault data demonstrate that the global average correlation coefficient effectively screens out redundant features in the dataset that negatively impact fault diagnosis results, thereby improving diagnosis efficiency and accuracy. The LAFA-Net model, capable of accurately diagnosing multiple types of pitch faults, shows a superior classification effect and accuracy compared to several advanced models, along with a faster convergence speed.

Renewable energy producers in coupled electricity and carbon markets face multi-dimensional uncertainties with cross-domain correlations. This paper proposes T-CMRS, an integrated forecasting optimization system for wind-solar-storage portfolios enhanced by fractional-order memory-aware uncertainty characterization. T-CMRS comprises (1) a transformer-based probabilistic forecasting engine capturing long-range temporal dependencies; (2) a fractional-order uncertainty modeling module employing Caputo derivatives to capture memory effects in price dynamics; and (3) a CVaR-based risk-averse optimization module reformulated as a linear program. Case studies on modified IEEE systems demonstrate that T-CMRS achieved 8.7% higher average daily profit than deterministic methods with 33.3% lower volatility, 15% VaR improvement over stochastic programming, and 12.3% scenario generation error reduction via fractional-order modeling. Scalability analysis confirms tractable computation for 500-bus systems, verifying applicability to large-scale deployments.