Accurate forecasting of offshore wind power output is particularly challenging owing to the resource's stochasticity and instability. Uncertainty modeling in wind power forecasting not only reveals output volatility but also underpins safe grid operation. For the first time, this paper presents a novel two-stage framework for offshore wind power uncertainty forecasting, combining deterministic point forecasts with probabilistic scenario generation. The proposed method combines Frequency Enhanced Decomposed Transformer (FEDformer) for deterministic prediction and Seasonally Conditional Decomposed Diffusion Model (SDCDM) for scenario generation. FEDformer enhances multi-scale feature extraction through frequency decomposition, while SDCDM applies seasonal decomposition and conditional diffusion to generate diverse probabilistic scenarios. The model demonstrates strong performance in MRAE, NAPS, and CRPS metrics, indicating excellent predictive accuracy and reliable uncertainty quantification.

Accurately estimating demand response (DR) potential is challenging in regions without historical DR programs. This paper presents an unsupervised, clustering-based framework that infers regional DR potential directly from smart-meter load data. The pipeline includes (i) data cleansing and normalization; (ii) customer segmentation using DRL-DBSCAN and RW-Clustering to uncover consumption regularities and latent flexibility; and (iii) aggregation of segment-level flexibility to form regional DR potential indices. A case study on the Low Carbon London (LCL) smart-meter trial uses half-hourly load measurements from 487 residential customers to quantify the performance of the proposed method. Compared with a conventional k-means baseline, the proposed DRL-DBSCAN plus RW-Clustering pipeline improves the Davies–Bouldin index from 4.9545 to 2.1642 and the Xie–Beni index from 10.7438 to 6.6637, yielding more compact and better-separated typical daily load profiles and more reliable DR potential estimates. The resulting probability distributions of upward and downward DR potential across 48 half-hourly time steps provide a quantitative basis for targeting flexible customer segments and prioritizing DR deployment. The proposed method supports distribution-level planning and local grid operation—especially in areas where DR infrastructure is nascent—and offers a scalable tool for integrating demand-side flexibility into renewable-rich power systems.

Hydropower plays a key regulating role in new-type power systems, and both forecasting accuracy and interpretability are critical for power dispatch. However, cascade hydropower forecasting is constrained by strong spatiotemporal coupling among multi-dimensional features, flow propagation delays, as well as the limited transparency of deep learning models. To tackle these issues, this paper develops a hybrid framework integrating Maximal Information Coefficient (MIC), the Long- and Short-term Time-series Network (LSTNet), and the SHapley Additive exPlanations (SHAP) interpretability method. First, an MIC-based nonlinear screening mechanism is employed to remove redundant noise and construct a high-quality input space. Second, an LSTNet model is developed to deeply extract spatiotemporal coupling features among cascade stations and flow evolution patterns, achieving high-accuracy forecasting of both system-level and station-level outputs. Finally, SHAP is used for global and local interpretability analysis to perform physics-consistency verification with respect to the model's decision-making rationale. Experimental results indicate that the proposed approach achieves low errors in total output forecasting, reducing error levels by approximately 57-88% compared with Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Informer. Moreover, SHAP feature-dependence analysis reveals a nonlinear response change of station D around 7.8 MW, providing evidence for the physical consistency of the model outputs and improving model interpretability.

The occurrence of extreme disasters, such as seismic hazards, can significantly disrupt transportation and distribution networks (DNs), consequently impacting the post-disaster recovery process. Restoring load using distributed generation represents an important approach to improving the resilience of DNs. However, using these resources to provide resilience is not enough to justify having them installed economically. Therefore, this paper proposes a two-stage stochastic mixed-integer programming (SMIP) model for the configuration of stationary energy storage systems (SESSs) and mobile energy storage systems (MESSs) during earthquakes. The proposed model comprehensively considers both normal and disaster operation scenarios of DNs, maximizing the grid’s economic efficiency and security. The first stage is to make decisions about the location and size of energy storage, using a hybrid configuration scheme of second-life batteries (SLBs) for SESSs and fresh batteries for MESSs. In the second stage, the operating costs of DNs are evaluated by minimizing normal operating costs and reducing load loss during seismic events. Additionally, this paper proposes a scenario reduction method based on hierarchical sampling and distance reduction to generate representative fault scenarios under varying earthquake magnitudes. Finally, the progressive hedging algorithm (PHA) is employed to solve the model. The case studies of the IEEE 33-bus and 12-node transportation network are conducted to validate the effectiveness of the proposed method.

Air conditioning loads in power systems exhibit spatiotemporal heterogeneity across geographical regions, complicating accurate load forecasting. This study proposes a framework that integrates Deep Reinforcement Learning-guided DBSCAN (DRL-DBSCAN) clustering with a Graph Attention Network (GAT)-based Graph Neural Network to model spatial dependencies and temporal dynamics. Using meteorological features like temperature and humidity, the framework clusters geographical grids and applies GAT to capture spatial patterns. On a Pecan Street dataset of 25 households in Austin, the GAT with DRL-DBSCAN achieves a Test MSE of 0.0216 and MAE of 0.0884, outperforming K-Means (MSE: 0.0523, MAE: 0.1456), Hierarchical clustering (MSE: 0.0478, MAE: 0.1321), no-clustering (MSE: 0.0631, MAE: 0.1678), LSTM (MSE: 0.3259, MAE: 0.3442), Transformer (MSE: 0.6415, MAE: 0.4835), and MLP (MSE: 0.7269, MAE: 0.5240) baselines. This approach enhances forecasting accuracy for real-time grid management and energy efficiency in smart grids, though further refinement is needed for standardizing predicted load ranges.

The growing demand for reliable renewable energy underscores the pivotal role of offshore wind power, renowned for its consistent and robust wind speeds. However, harsh weather conditions often lead to sensor failures and communication disruptions at sea, resulting in missing wind speed data. Such data gaps significantly hinder the accuracy of wind power forecasting, power curve modeling, and energy assessments of wind turbines-critical tasks for efficient operation and maintenance. To address these challenges, this work introduces an innovative imputation framework for missing wind speed data in offshore wind farms, leveraging a conditional diffusion model. By framing the imputation as a conditional generation problem, the approach employs multihead attention mechanisms and graph convolutional networks to effectively capture spatiotemporal correlations and generate context-aware information. A denoising network then transforms random noise into accurate estimates for the missing values, while adaptive bandwidth kernel density estimation (ABKDE) is used to estimate the distribution of missing wind speed, providing probabilistic intervals for imputation. Extensive experiments on real-world datasets across a variety of missing data scenarios demonstrate that the proposed method outperforms existing benchmarks. Not only does it yield precise deterministic imputation results, but it also quantifies uncertainty by providing probabilistic intervals for the imputed values. This significantly enhances the reliability and accuracy of wind speed imputation. Experiments have demonstrated that the proposed method is particularly effective in handling complex missing data patterns, such as those caused by long-term sensor failures or extreme weather events, and it can improve the performance of downstream prediction tasks. This work provides a novel and robust solution for missing data imputation in offshore wind farms, offering more reliable and interpretable results for downstream tasks, including risk management and wind power optimization.

Modern power systems are increasingly complex, and the risk of transient instability is rising accordingly. Data-driven transient stability assessment (TSA) is attractive for its efficiency, yet in practice the number of unstable events is much smaller than that of stable ones, leading to severe class imbalance and degraded accuracy. This paper proposes a SHAP-guided, classifier-controlled diffusion augmentation framework to mitigate imbalance and enhance TSA. First, SHAP analysis identifies critical unstable and near-boundary samples, ensuring that augmentation targets the most informative regions of the state space. Then, a classifier-guided conditional diffusion model—with a Transformer-based denoising network—generates class-faithful synthetic trajectories that capture long-range temporal dependencies and inter-variable couplings. Case studies on the IEEE 10-machine 39-bus system show that the proposed method consistently surpasses traditional over-sampling (e.g., SMOTE/ADASYN) and deep generative baselines (e.g., CGAN/TimeGAN) in terms of accuracy, precision, recall, and F1-score. Moreover, the approach maintains strong performance under small-sample settings and shortened time-series inputs, demonstrating favorable adaptability and robustness. These results indicate that the proposed augmentation framework offers a practical and effective solution for TSA under severe class imbalance.

Accurate identification of network topology and line parameters is essential for effective management of distribution systems. An innovative joint estimation method for distribution network topology and line parameters is presented, utilizing a power flow graph convolutional network (PFGCN). This approach addresses the limitations of traditional methods that rely on costly voltage phase angle measurements. The node correlation principle is applied to construct a node correlation matrix, and a minimum distance iteration algorithm is proposed to generate candidate topologies, which serve as graph inputs for the parameter estimation model. Based on the topological dependencies and convolutional properties of AC power flow equations, a PFGCN model is designed for line parameter estimation. Parameter refinement is achieved through an alternating iterative process of pseudo-trend calculation and neural network training. Training convergence and loss function values are used as feedback to filter and validate candidate topologies, enabling precise joint estimation of both topologies and parameters. The proposed method’s accuracy, transferability, and robustness are demonstrated through experiments on the IEEE-33 and modified IEEE-69 distribution systems. Multiple metrics, including MAPE, IAE, MAE, and R2, highlight the proposed method’s advantages over Adaptive Ridge Regression (ARR). In the C33 scenario, the proposed method achieves MAPEs of 4.6% for g and 5.7% for b, outperforming the ARR method with MAPEs of 7.1% and 7.9%, respectively. Similarly, in the IC69 scenario, the proposed method records MAPEs of 3.0% for g and 5.9% for b, surpassing the ARR method’s 5.1% and 8.3%.

This study seeks to improve the accuracy of air conditioning load forecasting to address the challenges of load management in power systems during high-temperature periods in the summer. Given the limitations of traditional forecasting models in capturing different frequency components and noise within complex load sequences, this paper proposes a multi-level decomposition forecasting model using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), sample entropy (SE), variational mode decomposition (VMD), and long short-term memory (LSTM). First, CEEMDAN is used for the preliminary decomposition of the raw air-conditioning load series, with modal components aggregated by sample entropy to generate high-, medium-, and low-frequency subsequences. VMD then performs a secondary decomposition on the high-frequency subsequence to reduce its complexity, while LSTM is applied to each subsequence for prediction. The final prediction result of the air-conditioning load is obtained through reconstruction. To validate model performance, this paper uses air-conditioning load data from Nanchong City and Sichuan Province, for experimental analysis. Results show that the proposed method significantly outperforms the LSTM model without decomposition and other benchmark models in prediction accuracy, with the Root Mean Square Error (RMSE) reductions ranging from 40.26% to 74.18% and the Modified Mean Absolute Percentage Error (MMAPE) reductions from 37.75% to 73.41%. By employing the SHAP (Shapley additive explanations) method for both global and local interpretability, the model reveals the influence of key factors, such as historical load and temperature, on load forecasting. The decomposition and aggregation approach introduced in this paper substantially enhances forecasting accuracy, providing a scientific foundation for power system load management and dispatch.

Electricity prices behave more irregular patterns due to uncertainties and effects of mixed-temporal primary energy markets. Thus, it is challenging to precisely forecast them. To conquer this barrier, an interpretable interval prediction method that seamlessly unifies cross-energy and electricity markets is proposed. At the outset, to clarity the feature rising the aberrant electricity prices, several exogenous, and multitemporal features from other primary energy markets, such as natural gas and coal markets, are unified to settle our database. Then, a Gaussian mixture model (GMM)-lightweight gradient boosting machine hybrid detector is presented to isolate and foresee the outlier sequence of electricity prices. A hybrid LSTNet-kernel density estimation (LSTNet-KDE) method is further proposed to enable outlier-adaptive interpretable interval prediction. Specifically, the LSTNet contributes to amalgamating multitemporality across markets and predicting the principal trends, and the KDE serves to encapsulate the uncertainty for the GMM-foreseen outliers. The method further merges with the Shapley additive explanations technique, such that exogenous latent features that induce electricity prices outliers can be finally comprehended. The numerical study on the real-world Danish electricity market verifies that, our proposed method beats other rivals in terms of precision, especially notable in forecasting outliers of electricity prices.

Accurate load forecasting, especially in the short term, is crucial for the safe and stable operation of power systems and their market participants. However, as modern power systems become increasingly complex, the challenges of short-term load forecasting are also intensifying. To address this challenge, data-driven deep learning techniques and load aggregation technologies have gradually been introduced into the field of load forecasting. However, data quality issues persist due to various factors such as sensor failures, unstable communication, and susceptibility to network attacks, leading to data gaps. Furthermore, in the domain of aggregated load forecasting, considering the potential interactions among aggregated loads can help market participants engage in cross-market transactions. However, aggregated loads often lack clear geographical locations, making it difficult to predefine graph structures. To address the issue of data quality, this study proposes a model named adversarial graph convolutional imputation network (AGCIN), combined with local and global correlations for imputation. To tackle the problem of the difficulty in predefining graph structures for aggregated loads, this study proposes a learnable adjacency matrix, which generates an adaptive adjacency matrix based on the relationships between different sequences without the need for geographical information. The experimental results demonstrate that the proposed imputation method outperforms other imputation methods in scenarios with random and continuous missing data. Additionally, the prediction accuracy of the proposed method exceeds that of several baseline methods, affirming the effectiveness of our approach in imputation and prediction, ultimately enhancing the accuracy of aggregated load forecasting.

Accurate anticipation of photovoltaic (PV) power generation in advance is crucial for renewable energy development, infrastructure planning, efficient power grid operations, and energy management. Emerging data-driven methods represented by deep learning have provided effective solutions for PV power generation forecasting. However, conventional data-driven forecasting algorithms rely heavily on extensive historical data, making it challenging to predict the output of newly-built PV plants (NPP) due to limited data availability. To address this concern, a novel physics-infused transfer learning model is proposed for short-term cross-plant PV power prediction, which leverages the public prediction knowledge learnt from relevant PV plants to develop a predictor compatible with NPP. Key innovations include: (1) Firstly, we propose a forecasting-oriented Domain Adversarial Neural Network (DANN) that incorporates Wasserstein distance, enabling the reduction of the discrepancy in the feature vector distribution between source and target plants through iterative adversarial training. The feature vectors from NPP would be compatible with a predictor trained on the feature vectors from data-rich PV plants. (2) Secondly, this framework implicitly transfers the intricate regression patterns from data-rich PV plants to NPP with limited historical measurements, allowing for the capture of short-term fluctuations using real-time data as input. (3) Subsequently, a well-calibrated physical model chain enables the refined and stabilized numerical calculations in the conversion from solar irradiance to PV power output, thus extending the forecasting horizon. (4) Finally, the Bayesian combination model (BCM) is deployed to coordinate the two sub-predictors, enabling simultaneous prediction of trends and short-term fluctuations. The hybrid framework is formulated and validated adopting real-world PV data from four PV plants in North China. Simulation results indicate that the prediction accuracy outperforms all selected benchmark models. Compared to standalone models trained on the scarce data of NPP, the transfer learning-based model can reduce prediction errors by approximately 20% to 68%. Moreover, the proposed model demonstrates excellent generalizability and robustness, effectively mitigating the effects of geographical disparities among source and target domains, the performance of cross-geographic region transfer forecasting task is improved by 30%- 40% compared to the traditional alternative.

Electricity prices are a central element of the electricity market, and accurate electricity price forecasting is critical for market participants. However, in the context of increasingly integrated economic markets, the complexity of the electricity system has increased. As a result, the number of factors required to consider in electricity price forecasting is growing. In addition, the high percentage of renewable energy penetration has increased the volatility of electricity generation, making it more challenging to predict prices accurately. In this paper, we propose a probabilistic forecasting method based on SHAP (SHapley Additive exPlanation) feature selection and LSTNet (long- and short-term time-series network) quantile regression. First, to reduce feature redundancy and overfitting, we use the SHAP method to perform feature selection in a high-dimensional input feature set, and specifically analyze the magnitude and manner in which features affect electricity prices. Second, we apply the LSTNet quantile regression model to predict the electricity value under different quantiles. Finally, the probability density function and the prediction interval of the predicted electricity prices are obtained by kernel density estimation. The case of the Danish electricity market validates the effectiveness and accuracy of our proposed method. The accuracy of the proposed method is better than that of other methods, and we assess the importance and direction of the impact of features on electricity prices.

Under the "carbon peaking and carbon neutrality" goals, a high proportion of renewable energy connected to the distribution system gives rise to high operating costs and excessive power loss of wind turbine generators. To solve these problems,a dynamic reconfiguration method of distribution system is proposed in this paper,which takes carbon trading mechanism and demand response into consideration. First, the garbage-fueled power station is connected to the distribution system in the form of distributed power supply to improve the energy distribution structure of the system and improve the operation stability and economy of the distribution network system. Second, the carbon trading mechanism and demand response are introduced respectively to build a dynamic distribution network reconstruction model considering carbon trading mechanism and demand response.Third,the second order cone relaxation method is used to simplify the non-convex conditions and reduce the difficulty of solving them. Finally,based on the improved IEEE33 node distribution network model, the influence of the proposed method on the total operating cost of the system,wind turbine generators power loss and node voltage is analyzed. The results of the example show that the distribution system reconfiguration method considering carbon trading mechanism and demand response can significantly reduce the total operating cost and power loss of wind turbine generators.

China's distribution network system is developing towards low carbon, and the access to volatile renewable energy is not conducive to the stable operation of the distribution network. The role of energy storage in power regulation has been emphasized, but the carbon emissions generated in energy storage systems are often ignored. When planning energy storage, increasing consideration of carbon emissions from energy storage can promote the realization of low-carbon power grids. A two-layer energy storage planning strategy for distribution networks considering carbon emissions is proposed. The upper layer uses regional typical daily load to calculate voltage-active power sensitivity to lessen candidate addresses. At the lower level, we have constructed a carbon emission model for the distribution network, and further consider the cost of energy storage to achieve capacity allocation with the goal of minimizing. We have verified the effectiveness of this method on an improved IEEE33 network, indicating that the energy storage strategy can effectively reduce carbon emissions under the premise of reducing the total cost.

水电是可再生能源的重要组成部分,精确预测水电站的发电量对电力系统的运行和调度至关重要.针对传统预测方法在处理水电站之间复杂的拓扑结构时存在限制的问题,提出了一种基于图迁移学习的方法,旨在通过水电站的拓扑连接特征提升发电预测的准确性和泛化能力.利用水电站的拓扑结构构建图表示各水电站之间的关联关系,以捕捉水电站的上下游关联特征,采用预训练源水电站数据集并通过图迁移学习来适应目标水电站的发电预测模型.实验结果表明,图迁移学习有助于更好地捕捉水电站间的拓扑特征,提高发电预测精度,减少所需训练样本数量.

Under the background of educational informatization,the combination of online teaching and offline classroom teaching——the construction of blended teaching mode is the focus of current teaching reform.Facing the construction of new engineering,training students to solve complex engineering problems and innovation ability is the primary problem of engineering colleges and universities.In the teaching practice of electrical engineering course,the course teaching reform practice is implemented,which is based on the knowledge systemization construction,aimd at the combination of theory and practice,guided by the CDIO engineering education concept,and taking PBL as the specific implementation way.By adopting CLFEDM way to establish the teaching goal,building inquiry,progressive class teaching design,based on CDIO-PBL teaching mode,establishing a diversified performance evaluation system of teaching evaluation and examination,the courses achieves better teaching results,improving the effect of classroom teaching,cultivating the students'consciousness of engineering and innovation,and improving the students'comprehensive ability to solve problems.

富集地区的小水电出力建模是保证电网安稳与经济运行、实现大小水电协调的重要措施.位于偏远山区的小水电信息采集困难,建模相关有效数据匮乏,难以借鉴现有的大中型水电出力研究方法.针对贫资料地区小水电,将迁移学习引入其出力建模,基于卷积神经网络(convolutional neural network,CNN)与长短期记忆网络(long short-term memory,LSTM)混合的迁移卷积时空网络(transfer convolutional neural network-long short term memory,TCNN-LSTM),提出了一种样本数据迁移学习方法.以一组具有代表性的丰富水电长期运行数据库为源域;首先,为使迁移前后的任务数据域更相近,提出了跨水电相似数据匹配算法,对源域多维度的长期数据进行时序分割,并计算各子序列与目标水电短期数据的匹配度,筛选高相似片段提纯源域,以提高迁移学习模型的正向迁移率与准确度;然后,利用卷积时空网络(convolutional neural network-long short term memory,CNN-LSTM)对源域进行预训练并提取公共知识,通过网络参数微调(fine-tuning,FT)的方式将预训练模型外推到数据稀缺的目标小水电中,以实现少样本条件下的数据特征迁移学习.最后,以四川某地区为实例验证该算法在贫资料小水电样本数据欠缺情况下的有效性与鲁棒性,相比传统深度学习,本方法将预测均方根误差平均降低16.54％,具有一定工程实用价值.

Historical data scarce and varying patterns of new built run-off small hydropower (RSHP) limits precise power generation prediction. Unforeseen hydropower can induce uneconomic power grid operations. To address this issue, a novel transfer learning method enabling integration of public RSHP knowledge is proposed. First, a RSHP data matching algorithm is proposed to pre-filter similar source domain data and produce a RSHP database matching patterns of target RSHP. This algorithm allows us to improve performance of transfer learning model. Next, public prediction knowledge implicated in the RSHP database is learned towards a CNN-BiLSTM hybrid pre-trained network. Then, the pre-trained network is transferred to the target RSHP prediction models by hyper-parameter fine-tuning algorithm, which reduces divergence between the pre-trained network outputs and the target domain data. As a result, accurate new RSHP prediction models can be generated under the challenge of data lack. At the last, the RSHP prediction models are fed back to the fine-tuning algorithm such that generalizability of the models enables life-long self-renewal. The real-world case demonstrates the superiority of the proposed method in terms of accuracy and data utilization. The average prediction error of the proposed method is 16.27% lower than the best traditional alternative.