31 January 2022 in IEEE Transactions on Power Systems
Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forecasting model's accuracy. To solve this problem, this paper proposes an integrated missing-data tolerant model for probabilistic PV power generation forecasting. Taking historical PV generations as input, this model is based on a recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead forecasting of the probability distribution of PV generation. The unobserved input data will be imputed recursively based on the model output at the previous time step. During the training process, the imputations and forecasting values are iteratively updated by the negative log-likelihood loss function. As a salient advantage, this method can deal with data missing scenarios at both offline and online stages. Numerical experiments are conducted on two one-year datasets from Australia and Singapore, respectively. Probabilistic forecasting for both large-scale and small-scale building-level PV power generation is tested at the time resolution of 15 mins. Testing results show the proposed method can achieve superior probabilistic prediction accuracy as well as strong robustness under various data missing scenarios, compared to other state-of-the-art methods.
11 May 2020 in IEEE Transactions on Industrial Informatics
Load shedding (LS) is an effective control strategy against voltage instability in power systems. With increasing uncertainties and complexity in modern power grids, there is a pressing need for faster and more accurate control decisions. In this paper, a hierarchical data-driven method is proposed for on-line prediction of event-based load shedding (ELS) against fault-induced delayed voltage recovery (FIDVR). The ELS problem is hierarchically modeled as a multi-output classification subproblem for identifying the best shedding location and a regression subproblem to predict the minimum shedding amount. To solve the two subproblems, the weighted kernel extreme learning machine (WKELM) is adopted to construct a direct mapping between system pre-fault operating conditions and corresponding control variables. The method is tested on ELS database which is analytically generated via a novel adaptive sensitivity-based process on the New-England 39-bus system.
24 August 2023 in IEEE Internet of Things Journal
Enhanced by machine learning (ML) techniques, data-driven stability assessment (SA) in smart cyber–physical grids has attracted significant research interest in recent years. However, the current centralized ML architectures have limited scalability, are vulnerable to privacy exposure, and are costly to manage. To resolve these limitations, we propose a novel secure distributed SA method based on federated learning (FL) and differential privacy (DP), namely, Secure Federated SA (SecFedSA). It leverages local system operating data to predict and estimate the system stability status and optimize the power systems in a decentralized fashion. In order to preserve the privacy of the distributed SA operating data, SecFedSA incorporates Gaussian mechanism into DP. Theoretical analysis on the Gaussian mechanism of SecFedSA provides formal DP guarantees. Extensive experiments conducted on the New England 10-machine 39-bus testing system and the synthetic Illinois 49-machine 200-bus testing system demonstrate that the proposed SecFedSA method can achieve advantageous SA performance, while protecting the privacy of the local model information compared to the state of the art.
18 November 2022 in IEEE Transactions on Power Systems
With the advancement of machine learning techniques, data-driven power system dynamic security assessment (DSA) has received great research interests. Traditional methods usually apply one DSA model for one specific fault and cannot simultaneously address different multiple faults by one model. To solve this issue and further improve the DSA accuracy performance, this paper proposes a novel DSA method based on multi-label learning (MLL) with a training database for sufficient and incomplete/uneven coverage labels scenarios. By considering fault correlation between different faults, the proposed MLL-based DSA method can handle multiple faults simultaneously with the high stability assessment accuracy performance. Moreover, this paper provides the detailed optimization process and tight mathematical proof for the proposed MLL-based DSA method. Comprehensive simulation tests and comparisons were conducted on the New England 10-machine 39-bus testing system and the synthetic Illinois 49-machine 200-bus testing system.
17 March 2025 in IEEE Transactions on Automation Science and Engineering
This paper proposes a novel multi-task learning approach based on spatial-temporal recurrent imputation network (SRIN) for power system short-term voltage stability (STVS) assessment with incomplete PMU measurements. The state-of-the-art data imputation methods are based on single and separated learning tasks, which lack optimality for fully exploiting the information in available data. They are also facing several challenges in practical applications, e.g., dependence on complete datasets for training, and performance degradation under continuous data missing scenarios. As a significant advantage, the proposed SRIN method jointly optimizes the objective of missing value imputation and stability prediction through a multi-task recurrent network model. In this way, the integrated model can fully learn from any available data in the incomplete historical database, and the performance of both tasks can benefit from knowledge sharing and transferring across tasks. Moreover, the proposed method has superior advantages in handling both spatial and temporal consecutive missing scenarios, where the imputations are derived by an intelligent combination of history-based and feature-based estimations. Numerical simulation results on two test systems show that, under any PMU missing condition, the proposed method can maintain a competitively high STVS assessment accuracy with a much less imputation error.
20 January 2025 in IEEE Transactions on Power Systems
This letter proposed a hybrid credibility learning method for data-driven Dynamic Security Assessment (DSA), aiming to enhance the trustworthiness of DSA results under out-of-distribution changing system conditions. The proposed method integrates multiple credibility criteria as learning inputs, combining model consistency—reflected through the output distribution of ensemble learners—with novel indicators of data disparities, namely the Degree of Outlier (DOO) and One-sample Maximum Mean Discrepancy (O-MMD). Moreover, the credibility model benefits from training on a specifically designed out-of-distribution dataset which is further reinforced through misclassified DSA instances. This letter also provides a comprehensive comparison of existing credible DSA methods via the proposed trustworthiness evaluation index. Simulation results on the benchmark testing system show that the proposed method can achieve the best trade-off between DSA accuracy and credibility under various extreme system conditions.