Leveraging both temporal and spatial correlations to predict wind speed remains one of the most challenging and less studied areas of wind speed prediction. In this paper, the problem of predicting wind speeds for multiple sites is investigated by using the spatio-temporal correlation. We proposed a deep architecture termed predictive spatio-temporal network (PSTN), which is a unified framework integrating a convolutional neural network (CNN) and a long short-term memory (LSTM). Initially, the spatial features are extracted from the spatial wind speed matrices (SWSMs) by the CNN at the bottom of the model. Then, the LSTM captures the temporal dependencies among the spatial features extracted from contiguous time points. Finally, the predicted wind speeds are given by the last state of the top layer of the LSTM, which are generated by using the spatial features and temporal dependencies. Though composed of two kinds of architectures, PSTN is trained with one loss function in an end-to-end (E2E) manner, which can learn temporal and spatial correlations jointly. Experiments for short-term predictions are conducted on real-world data, whose results demonstrate that PSTN outperforms prior methods.

Wind speed prediction with spatio–temporal correlation is among the most challenging tasks in wind speed prediction. In this paper, the problem of predicting wind speed for multiple sites simultaneously is investigated by using spatio–temporal correlation. This paper proposes a model for wind speed prediction with spatio–temporal correlation, i.e., the predictive deep convolutional neural network (PDCNN). The model is a unified framework, integrating convolutional neural networks (CNNs) and a multi-layer perceptron (MLP). Firstly, the spatial features are extracted by CNNs located at the bottom of the model. Then, the temporal dependencies among these extracted spatial features are captured by the MLP. In this way, the spatial and temporal correlations are captured by PDCNN intrinsically. Finally, PDCNN generates the predicted wind speed by using the learnt spatio–temporal correlations. In addition, three error indices are defined to evaluate the prediction accuracy of the model on the wind turbine array. Experiment results on real-world data show that PDCNN can capture the spatio–temporal correlation effectively, and it outperforms the conventional machine learning models, including multi-layer perceptron, support vector regressor, decision tree, etc.

A probabilistic load flow (PLF) method using Copula and improved Latin hypercube sampling is proposed. The stochastic dependence between input random variables is considered. Copula theory is adopted to establish the probability distribution of correlated input random variables. Based on discrete data, an improved Latin hypercube sampling is proposed. The accuracy of probability distribution of correlated input random variables established by Copula theory is evaluated by adopting the power output of wind farms located at New Jersey. The performance of the proposed PLF method is investigated using IEEE 14‐bus and IEEE 118‐bus test systems.

Phasor measurement unit (PMU) data manipulation attacks (PDMAs) may blind the control centers to the real-time operating conditions of power systems. Detecting these attacks accurately is essential to ensure the normal operation of power system monitoring and control. Using long-term accumulated historical PMU measurements to train a machine learning model to detect PDMAs has shown promising results. In this paper, deepautoencoder-based anomaly measurers are deployed throughout the power system to build a distributed PDMA detection framework. The architecture of a deep autoencoder and its training process are introduced. How to convert the historical PMU measurements into data samples for learning is also elaborated upon. Once trained, an anomaly measurer can assess the PDMA existence possibility of the new PMU measurements. By integrating the results of different anomaly measurers, the proposed distributed PDMA detection framework can detect PDMAs in the whole power system. The effectiveness and detection performance of the framework are discussed through experiments.

Leveraging multiple heterogeneous measurements to predict wind power has long been a challenging task in the electrical community. In this paper, a deep architecture incorporated with multitask learning and multimodal learning for wind power prediction, termed predictive stacked autoencoder (PSAE), is presented. PSAE is a unified framework integrating multiple stacked autoencoders (SAEs), one feature fusion layer, and one prediction terminal layer, which expands the architecture from two spatial dimensions, including the depth and width, compared to conventional prediction models. Initially, the SAEs at the bottom of PSAE extracted features from multiple kinds of measurements respectively. Following, the feature fusion layer encodes the high-order features extracted by different SAEs into a unified feature that is more informative and representative for wind power prediction. Finally, the prediction terminal layer functions as a regression machine which generates the predicted targets based on the fusion features. Trained in an end-to-end (E2E) manner, PSAE is capable of learning heterogeneous features jointly and achieving the prediction task of sequence-to-sequence (S2S). Experiments for multi-step short-term predictions are conducted on real-world data, and the results demonstrate the superiority of PSAE to prior methods.

This paper introduces an advanced approach for optimizing the distribution network reconfiguration (DNR) with the placement and sizing of multiple types of distributed generators (DGs). The method employs the ant colony optimization algorithm (ACOA), which is an innovative adaptive optimization algorithm, while also considering the system’s reliability. The primary objectives of the optimization problem are to minimize active power loss (APL), reduce voltage drop ( V_D ) on buses, enhance system stability (SS), and improve overall reliability by reducing energy not supplied (ENS) to end-users. The optimization process involves determining the optimal location and size of DGs in the radial distribution network (RDN) using the ACOA meta-heuristic. The method maintains the radial structure of the system by selectively opening lines during the DNR process. The proposed technique is evaluated through simulations carried out on the IEEE-33 & -69 bus RDNs under various scenarios. The results demonstrate the superiority of the presented ACOA-based approach over other techniques, such as fireworks algorithm (FWA) and adaptive shuffled frogs leaping algorithm (ASFLA). Combining the DNR and DGs placement in a simultaneous manner yields the best performance for the distribution network, resulting in lower APL, reduced V_D , improved SS, and enhanced reliability. Furthermore, considering reliability in the optimization process significantly reduces ENS for customers and enables meeting their maximum load demand. Overall, the concurrent consideration of DNR and DGs placement using ACOA proves to be more effective than alternative algorithms.