IET Renewable Power Generation最新文献

In this study, an innovative approach with enhanced recursive feature clustering for load forecasting in smart solar microgrids by integrating density-based spatial clustering (DBSCAN) and radial basis function neural networks (RBFNN) encoder is proposed. Our methodology is based upon novel density-based clustering with feature recursive forwarding RBFNN-LSTM for high-accuracy micro- and macro-feature learning in temporal data. DBSRad-LSTM performance is evaluated using three distinct datasets: Panama electricity consumption, Italy solar electric load, and a custom dataset tailored for smart grid applications. Through rigorous comparative analysis, our DBSRad-LSTM model outperformed traditional machine learning models such as gated recurrent unit (GRU), long short-term memory (LSTM), and convolutional neural networks (CNN) across several metrics. Specifically, DBSRad-LSTM demonstrated superior performance in terms of accuracy, thereby contributing enhanced load forecasting capabilities. The proposed model integrating RBFN linear functionality with the attention of LSTM and DBSCAN clustering to enhance the learning of temporal data outperformed CNN, SVMCNN, and GRU on Panama power consumption, Italy electric load and bespoke datasets, obtaining a higher R² value of 0.89 and much lower MSE 0.015, RMSE 0.123, and MAE of 0.009. Achieving a 9%–25% improvement in error metrics and an average 13% better fit. By offering a distinct clustering-based approach that improves on existing methods, this research makes a substantial contribution to the field of smart grid management and opens the door for more precise and effective energy distribution systems.

The volatility and intermittency of large-scale wind power grids are prominent under cold wave conditions. The traditional methods for determining reserve capacity are difficult to meet the requirements of grid stability. Therefore, this paper proposed a secondary reserve optimisation method for power systems with large-scale wind power considering cold waves. First, we proposed a wind power forecasting model based on XGBoost-Transformer to describe wind power output during cold waves. Second, a Security-Constrained Dynamic Economic Dispatch (SCDED) model based on robust optimisation is proposed. The model considers the impact of wind power forecast error, load fluctuation range, cold wave weather shock, N-1 thermal unit contingency and N-1 transmission line contingency. A two-stage algorithm based on Benders decomposition is employed to solve the proposed model and determine the secondary reserve capacity. Finally, a large number of experiments were carried out on the IEEE 30-bus system and a regional power grid in northern China. The results show that the Monte Carlo verification success rate of this method can reach up to 100% under cold wave conditions, which is superior to the comparison method. The research results can provide reference for improving the ability of the power grid to resist cold wave shocks.

With the increasing integration of large-scale renewable energy sources into the power grid, the issue of sub-synchronous oscillation (SSO) has become more pronounced, posing a significant threat to the safe and stable operation of the power system. This paper proposes a new method for the early and rapid detection of SSO using deterministic learning theory. A comprehensive database of oscillation patterns is constructed by simulating a variety of conditions that can induce grid oscillations, including wind speed and control parameters. A learning estimator is then developed to identify stable and oscillation dynamics. Furthermore, a knowledge bank for SSOs detection and isolation is also established, using the minimum residual principle, oscillation patterns matching those in the knowledge bank can be detected. Then, based on an example of grid-connected sub-synchronous oscillations in wind turbines are utilized to show the effectiveness of the proposed method. The detection accuracy of SSO is calculated as 94%, and the detection time in this paper is reduced to about 0.023 s.

To address the issue of insufficient consideration of wind turbine physical characteristics and wind farm meteorological features in wind power forecasting, this paper proposes an ultra-short-term wind power prediction model based on digital twin technology. The model constructs a digital twin forecasting framework that integrates a digital-physical model of the wind turbine and a parallel CTransformer-BiGRU model to enhance prediction accuracy. The deep learning module captures spatiotemporal features in the data, while the digital-physical model couples the forecasting process with the actual physical conditions of the wind farm, thereby improving prediction precision. Finally, the effectiveness of the proposed algorithm is validated through experimental tests on a real-world dataset from a wind farm in Xinjiang, China.

RETRACTION: A. Dehshiri Badi, V. Amir, and S. M. Shariatmadar, “Resilience-Orientated Expansion Planning of Multi-Carrier Microgrid Utilising Bi-Level Technique,” IET Renewable Power Generation no. 18 (2024): 1106–1128, https://doi.org/10.1049/rpg2.12854.

The above article, published online on 16^th September 2023 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the journal editor-in-chief, David Infield; the Institution of Engineering and Technology; and John Wiley & Sons Ltd.

The retraction has been agreed to due to concerns raised by a third party regarding the presence of a paragraph with multiple irrelevant citations in this article. The authors have not responded to our requests for addressing the concern raised. Furthermore, the paragraph that contains multiple irrelevant citations is a textual reproduction from multiple other manuscripts published by different author groups. Accordingly, we cannot vouch for the integrity or reliability of the content and have taken the decision to retract the article. The authors have been informed of the decision to retract the article.

Microgrids are critical for achieving smart grid objectives, enhancing reliability, resilience, and supplying under-served areas. However, day-ahead scheduling of generating resources remains challenging due to uncertainties inherent in renewable energy systems. Although stochastic optimization addresses uncertainties, conventional probability distribution functions (PDFs) used in scenario generation methods may yield sub-optimal outcomes. This study proposes an improved stochastic optimization method that selects hourly unique PDFs via best-fit criteria derived from forecasting errors. Forecasts for solar irradiance, load demand, and electricity prices were generated using an XGBoost model trained on data from the Australian Electricity Market Operator (2013–2020). Forecast errors were evaluated annually and hourly, testing various PDFs using Kolmogorov-Smirnov (KS) and Cramer Von-Mises (CvM) goodness-of-fit tests. Unit commitment (UC) and economic dispatch (ED) were then performed using Monte Carlo simulation, with 1000 scenarios reduced to 10 using the backward reduction method (BRM). To benchmark the proposed method, a robust optimization model with an ellipsoidal uncertainty set was implemented. Results showed that the proposed stochastic approach reduced total costs by 9%–39% compared to conventional fixed PDF selections. Compared to the optimal stochastic case, the robust approach incurred a moderate 13% cost overhead but outperformed some other traditional PDF cases. This confirms that while robust optimization offers conservative protection against uncertainty, the proposed data-driven unique PDF selection method delivers better economic performance, making it a valuable tool for microgrid operators and policymakers.

RETRACTION: A. Azarhooshang and A. Rezazadeh, “Energy Management of Distribution Network With Inverter-Based Renewable Virtual Power Plant Considering Voltage Security Index,” IET Renewable Power Generation no. 18, (2024): 126–140, https://doi.org/10.1049/rpg2.12902.

The above article, published online on 17^th December 2023 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the journal Editor-in-Chief, David Infield; the Institution of Engineering and Technology; and John Wiley and Sons Ltd.

The retraction has been agreed due to concerns raised by a third party regarding the presence of a paragraph with multiple irrelevant citations in this article. When the authors were asked to clarify these concerns, they did not address them adequately. Furthermore, the paragraph that contains multiple irrelevant citations is a textual reproduction from multiple other manuscripts published by different author groups. Accordingly, we cannot vouch for the integrity or reliability of the content and have taken the decision to retract the article. The authors have been informed of the decision to retract the article, and they disagree with the retraction.

With the increasing integration of distributed photovoltaics (PV), the risk profile of distribution transformers is becoming increasingly intertwined with meteorological factors. Meanwhile, global climate change has led to a rise in extreme weather events and greater interannual variability in meteorological conditions. As a result, traditional risk assessment methods, based on historical data, struggle to accurately predict future risks. To address this, this study proposes a long-term comprehensive risk assessment method for distribution transformers based on forecasted meteorological data. Firstly, the insulation aging risk of transformers is introduced, with the insulation aging process quantified through the transformer's insulation lifetime. Secondly, a random forest model is employed to enhance the temporal resolution of global climate models predictions. Using these forecasted meteorological data, the load factor of distribution transformers is predicted, generating potential operational scenes for these transformers. On this basis, a comprehensive risk assessment of distribution transformers is carried out by considering insulation lifetime loss, load loss due to transformer outage, and photovoltaic curtailment loss, employing a typical day method for risk evaluation. Finally, a case study of a distribution transformer in Shanghai is conducted to validate the superiority of risk assessment using forecasted data. The study also analyses the impact of PV integration on the overall risk of distribution transformers.

The increasing integration of solar photovoltaic (PV) systems into modern power grids highlights the need for advanced control strategies that ensure reliable voltage regulation under variable operating conditions. PV output is highly sensitive to irradiance and temperature fluctuations, which can degrade power quality and compromise grid stability. Conventional reinforcement learning-based controllers, such as deep deterministic policy gradient (DDPG), have shown promise, but their reliance on fixed hyperparameters limits adaptability, leading to performance deterioration during rapid solar variations. This paper proposes a novel adaptive meta-learning-based DDPG (AM-DDPG) controller implemented with a three-leg interleaved DC–DC boost converter for PV voltage regulation. The proposed controller employs a meta-learning mechanism to dynamically adjust key hyperparameters, including learning rate, stability factor, and noise scale, thereby improving responsiveness and adaptability. MATLAB simulations compare AM-DDPG with standard DDPG under slow, fast, and highly variable irradiance and temperature profiles. Results demonstrate that AM-DDPG achieves voltage stabilization within 10 ms, maintains a 566 V output with less than 0.1% deviation, and significantly suppresses voltage ripples. By enhancing dynamic performance and robustness, the proposed approach supports higher PV penetration and improves conversion efficiency. It also strengthens grid integration of renewable energy, contributing to sustainable and resilient low-carbon power systems.

As the ‘dual carbon’ goals continue to advance in China, the grid-connected scale of new energy power generation equipment such as wind power and photovoltaic power is constantly increasing. Transient overvoltage issues caused by fault disturbances are becoming increasingly frequent, significantly increasing the risk of cascading grid disconnection and equipment damage. Therefore, rapid and accurate assessment of transient overvoltage in new energy systems is of critical importance. This paper first analyses the characteristics of transient overvoltage in new energy sources under both electromagnetic and electromechanical transient models, comparing the trends in key electrical parameters under the two types of models. Then, to combine the advantages of high accuracy in electromagnetic transient models and high speed in electromechanical transient models, this paper uses the Morris global sensitivity analysis method to identify the key influencing factors of transient overvoltage peaks. Subsequently, the QR decomposition-based least squares method is employed to study the mapping relationship between overvoltage peaks in electromagnetic and electromechanical models. Finally, simulation verification confirms the accuracy of the mapping relationship. This method provides important references for system operation and maintenance, and also offers directions for further optimising system performance.