{"title":"Forecasting data-driven system strength level for inverter-based resources-integrated weak grid systems using multi-objective machine learning algorithms","authors":"","doi":"10.1016/j.epsr.2024.111112","DOIUrl":"10.1016/j.epsr.2024.111112","url":null,"abstract":"<div><div>Shortage of grid-fault level, known as system strength inadequacy, impacts on grid instability and can lead to blackouts. System strength is generally measured by short circuit ratio index at point of coupling (POC) of inverter-based resources (IBRs) and the grid system. Nowadays, accurate knowledge of system strength forecasting for ‘next day’ to ‘next week’ duration is essential to power system operators, owing to the higher-growth of IBRs. However, releavant publications about this subject remain limited when compared with load demand, active and reactive power prediction. Therefore, a data-driven system strength forecasting scheme is presented in this paper to surmount these issues. Multi-objective machine learning (MOML) algorithms are used to obtain the best result. The designed model uses energy management system (EMS) to collect historical online data and complete the training and testing procedures via learning frameworks such as Hedge-backpropagation neural network-based tangent function (Hedge-BPNNT), support vector machine (SVM) and long short-term memory (LSTM). The methodology is developed to predict up to seven days of system strength forecasting levels by using the last thirty-days data status. The designed model is tested on both simulated and experimented cases, confirming higher accuracy performance with reduced computational time when compared to existing literature.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Short-term load forecasting by GRU neural network and DDPG algorithm for adaptive optimization of hyperparameters","authors":"","doi":"10.1016/j.epsr.2024.111119","DOIUrl":"10.1016/j.epsr.2024.111119","url":null,"abstract":"<div><div>Short-term load forecasting (STLF) is critical to optimizing power system operation. Deep learning (DL) methods can provide extremely high accuracy for STLF. However, most models in existing research lack adaptive optimization capabilities in the prediction process and suffer from performance degradation. To resolve the above difficulties, we propose a hybrid model (DDPG-GRU) based on gated recurrent units and deep deterministic policy gradients for STLF. First, the GRU network has the advantage of processing multiple time series inputs and can simultaneously consider multi-dimensional load characteristics, thereby making the model more efficient. Since the GRU model structure is relatively complex, choosing a good set of hyperparameters is very difficult. Therefore, the purpose of using DDPG is to optimize the hyperparameters of the GRU model adaptively. The proposed model is a combination of DL methods and reinforcement learning. In order to prove the superiority of the proposed model, it is applied to the load data of Area 1 in China to perform single-step and multi-step load forecasting, respectively. The results show that DDPG-GRU has a better fitting effect than the baseline method. Taking the multi-step prediction results as an example, compared with the classic GRU network, the MAPE, MAE, and RMSE of the proposed model are reduced by 22.75 %, 14.44 %, and 14.02 %, respectively, while the <em>R</em><sup>2</sup> coefficient is increased by 13.23 %. At the same time, we use the China Area 2 data set to verify the universality of the proposed model. Furthermore, we compared the proposed method with state-of-the-art methods and achieved better accuracy.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Topology design of variable speed drive systems for enhancing power quality in industrial grids","authors":"","doi":"10.1016/j.epsr.2024.111114","DOIUrl":"10.1016/j.epsr.2024.111114","url":null,"abstract":"<div><div>In the last two decades, a rapid increase in the utilization of non-linear loads within electrical grids has been observed. Consequently, elevated levels of harmonics are found in both voltage and current waves, and adverse effects on power quality are caused. In this context, the variable speed drive (VSD) systems are considered a significant non-linear contributor. To mitigate the harmonic content in VSD systems, various techniques are explored, such as electronic smoothing inductor incorporation in the DC-link, active filters utilization at the grid side, and passive filters integration. A technique centered on the reconfiguration of the DC-link in the VSD systems is proposed in this paper to improve the overall performance of the VSD systems. The configuration comprises two transistors and two diodes, along with smoothing inductors and a capacitor to enhance power quality in the VSD systems. The utilization of three-stage sine pulse width modulation (SPWM) control technology ensures accurate control of the switches, generating optimal control signals that enhance the power quality of the voltage and current waves at the grid side. The effectiveness of the proposed approach is tested via time-domain simulation in MATLAB/Simulink under both constant and variable loading conditions and is verified using a laboratory prototype. The obtained results demonstrate a notable improvement in power quality, showcasing reduced total harmonic distortion (THD) in AC voltage and current waveforms, as well as minimized ripple factor in the DC-link when compared to existing methods.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Physics-informed machine learning for forecasting power exchanges at the interface between transmission and distribution systems","authors":"","doi":"10.1016/j.epsr.2024.111097","DOIUrl":"10.1016/j.epsr.2024.111097","url":null,"abstract":"<div><div>Power exchanges at Transmission–Distribution interfaces are crucial for both the Transmission System Operators (TSOs) and the Distribution System Operators (DSOs). In the past, simple hypothesis as a constant power factor sufficed for characterizing distribution networks and predicting power flows at Transmission–Distribution interfaces. However, the growing integration of distributed energy resources has led to an increased volatility in both active and reactive power flows, rendering traditional models less effective. This study presents a novel Physics-Informed Machine Learning (PIML) model designed to enhance the prediction of power exchanges at Transmission–Distribution interfaces. A novelty of the model lies in its combination of an Inverse Load Flow formulation, which defines an equivalent model of the distribution network (by calculating equivalent resistance and reactance using load flow equations), with classical data-driven regression techniques. Simulation results conducted on a modified version of the Oberrhein MV network highlight the superiority of the proposed PIML approach in front of full ML based methods, as demonstrated by a statistical indicator and an application-oriented evaluation. In addition, this research adopts the TSO perspective through a 2-step Optimal Power Flow analysis that integrates interface power predictions and enables the calculation of production and deviation costs. This multifaceted approach provides valuable insights into the practical implications of the power prediction accuracy on the TSO decision-making process and underscores the significance of accurate power exchange forecasts in the evolving electricity landscape.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An AC Z-bus-based distribution factors for contingency analysis of AC–DC networks","authors":"","doi":"10.1016/j.epsr.2024.111104","DOIUrl":"10.1016/j.epsr.2024.111104","url":null,"abstract":"<div><div>The AC–DC networks are susceptible to deliberate and unforeseen contingencies, much like any other traditional power network. Due to the complex form of the unified impedance matrix derived for the provided network, the classic <em>Z-bus</em>-based contingency analysis approach cannot comprehend the AC–DC network. The distribution factors thus obtained from a unified complex <em>Z-bus</em> lead to an indication of the flow of complex current for DC lines. Therefore, an alternative method to discover post-contingency consequences is looked for. A streamlined approach for visualizing an equivalent AC network for the given AC–DC network has been proposed in this work. The AC-equivalent network takes the original AC–DC network and recreates it using two parallel AC networks to get the requisite distribution factors. The ultimate current/power distributions of the original AC–DC network can be determined by applying the superposition rule to the parallel networks, by the linear characteristics of the suggested technique. With this, the standard AC-contingency analysis method to complete the steady-state contingency analysis for the AC–DC network can be utilized. The proposed approach has been validated by the encouraging outcomes achieved for AC–DC networks with <em>10, 13</em>, and <em>66</em> buses.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142327384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A dynamic pricing strategy and charging coordination of PEV in a renewable-grid integrated charging station","authors":"","doi":"10.1016/j.epsr.2024.111105","DOIUrl":"10.1016/j.epsr.2024.111105","url":null,"abstract":"<div><div>The increasing penetration of Plug-in Electric Vehicles (PEV) in the transportation system has increased the burden on the power system. This has made peak load demand management a challenging task for the power grid. To address this issue, a novel dynamic demand response pricing strategy in a grid-renewable generation integrated charging station environment is proposed in this paper. Renewable energy sources reduce the cost of generation and grid integration makes the system reliable. The proposed strategy models a Stackelberg game to provide dynamic prices for charging, discharging and grid power supplied for charging stations. Uncertainty and economics of renewable generation are considered for effective analysis and evaluation of the feasibility of the proposed strategy. The study considers the bidirectional flow of power and the battery degradation cost. Charging coordination is performed to optimize the cost of charging and discharging and support the grid in peak load demand management. Random charging behaviour and other parameters of PEVs are simulated using a random distribution function to resemble the real-time environment. A numerical case study validates that the proposed strategy has optimized the cost of charging and discharging and the serving capabilities of the charging station are enhanced with existing infrastructure.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142327382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Low frequency residential load monitoring via feature fusion and deep learning","authors":"","doi":"10.1016/j.epsr.2024.111092","DOIUrl":"10.1016/j.epsr.2024.111092","url":null,"abstract":"<div><div>Non-intrusive load monitoring (NILM) is a technique used to disaggregate the total power signal into individual appliance power signals, which plays an important role in smart grid. Recently, deep learning is widely used to deal with the NILM problem. However, current deep learning models are purely data-driven, which do not consider physical mechanisms, making them less effective in extracting useful features. To address these issues, a new approach for feature extraction based on variational mode decomposition (VMD) and a new deep learning model based on variational autoencoder (VAE) are developed in this paper. The proposed feature extraction approach extracts the pulse feature and concatenates it with the original power data to form multiple features, i.e., which achieves feature fusion to improve the performance of deep learning models better than with a single feature. In addition, a feedback variational mode decomposition (FVMD) is proposed to improve the decomposition performance of the original VMD. The channel attention mechanism is introduced to VAE to improve the performance of the model. To verify the accuracy and robustness of the proposed scheme in NILM, it is compared with the state-of-the-art models on the UK-DALE dataset, and the results show that the proposed feature extraction approach can greatly improve the performance of deep learning models and the proposed new deep learning model outperforms some state-of-the-art models in the realm of NILM.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quantifying the impact of flexibility asset location on services in the distribution grid: Power system and local flexibility market co-simulation","authors":"","doi":"10.1016/j.epsr.2024.111037","DOIUrl":"10.1016/j.epsr.2024.111037","url":null,"abstract":"<div><div>This research investigates the effectiveness of incorporating locational sensitivity factors into local flexibility market clearing mechanisms for effective congestion management and voltage regulation in distribution grids. A centralized local flexibility market optimization model is developed that considers technical and economic constraints. The study aims to explore the requirements for data availability, data quality, and reliable data exchange that can facilitate a broader range of flexibility services, thereby promoting the development of a local flexibility market. Sensitivity factors, including power transfer distribution factors, voltage sensitivity coefficients and transformer sensitivity coefficients, are used to quantify the impact of flexibility asset locations on congestion management and inform clearing rules. These static metrics are insufficient for establishing effective local flexibility market clearing rules when flexibility is procured by distribution system operators. The approach considers the state of the grid when calculating the sensitivity coefficients, which leads to a more accurate evaluation of flexibility bids, especially with regard to the impact of location on congestion management. The proposed mechanism for clearing the local flexibility market assumes continuous communication between the proposed local flexibility market operator and the distribution system operator for dynamic, iterative market clearing, which ensures the protection of grid data and a more accurate bid evaluation. The study demonstrates that the inclusion of locational information significantly increases the effectiveness of the proposed local flexibility market-based congestion management. The developed simulator for the proposed local flexibility market provides valuable insights into the interaction between the proposed local flexibility market and the distribution grid. The research results, derived from selected use cases, emphasize the importance of location-based sensitivity factors in the proposed local flexibility market clearing for distribution grids. The proposed approach offers a promising solution for optimizing congestion management and voltage regulation while ensuring efficient integration of distributed energy resources into distribution grids.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142318789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributed economic operation control in low-voltage resistive hybrid AC/DC microgrid clusters with interlinking converters","authors":"","doi":"10.1016/j.epsr.2024.110971","DOIUrl":"10.1016/j.epsr.2024.110971","url":null,"abstract":"<div><div>Connecting adjacent and diverse microgrids to form hybrid microgrid clusters improve the economic viability and the reliability of each microgrid in islanded operations. To realize the global economic operation among low-voltage resistive microgrid clusters, a two-level control strategy for subgrid control and microgrid clusters control is proposed in this study. In the case of subgrids, where the line impedance of the low-voltage grid is primarily resistive, we design the AC voltage increment droop (<em>V</em><sub>ac</sub>-IC) and the DC voltage increment droop (<em>V</em><sub>dc</sub>-IC) to effectively distribute power. The <em>V</em><sub>ac</sub>-IC and <em>V</em><sub>dc</sub>-IC droop controls cannot achieve economic power distribution due to the mismatched line impedances. Therefore, a distributed economic operation control based on the consensus algorithm is proposed in this study to eliminate the influence of mismatched line impedances on economic power distribution. In the context of microgrid clusters, the deviation of increment costs serves as an event-driven signal designed for Interlinking Converters (ILCs), aiming to optimize power exchange between adjacent subgrids. The coordination between the subgrid control and microgrid clusters control achieves global economic operation. Finally, Matlab/Simulink simulation verifies that the islanded hybrid microgrid clusters with the proposed strategy realize the economic operation well.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142318788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}