IET Renewable Power Generation最新文献

Reinforcement learning based two‐timescale energy management for energy hub 基于强化学习的能源枢纽双时标能源管理

IET Renewable Power Generation Pub Date : 2024-02-14 DOI: 10.1049/rpg2.12911

Jinfan Chen, C. Mao, Guanglin Sha, Wanxing Sheng, Hua Fan, Dan Wang, Shushan Qiu, Yunzhao Wu, Yao Zhang

{"title":"Reinforcement learning based two‐timescale energy management for energy hub","authors":"Jinfan Chen, C. Mao, Guanglin Sha, Wanxing Sheng, Hua Fan, Dan Wang, Shushan Qiu, Yunzhao Wu, Yao Zhang","doi":"10.1049/rpg2.12911","DOIUrl":"https://doi.org/10.1049/rpg2.12911","url":null,"abstract":"Maintaining energy balance and economical operation is significant for energy hub (EH) which serves as the central component. Implementing real‐time regulation for heating and cooling equipment within the EH is challenging due to their slow response time in response to the stochastic fluctuation in renewable energy sources and demands while the opposite is true for electric energy storage equipment (EST), a conventional single timescale energy management strategy is no longer sufficient to take into account the operating characteristics of all equipment. With this motivation, this study proposes a deep reinforcement learning based two‐timescale energy management strategy for EH, which controls heating & cooling equipment on a long timescale of 1 h, and EST on a short timescale of 15 min. The actions of the EST are modelled as discrete to reduce the action spaces, and the discrete‐continuous hybrid action sequential TD3 model is proposed to address the problem of handling both discrete and continuous actions in long timescale policy. A joint training approach based on the centralized training framework is proposed to learn multiple levels of policies in parallel. The case studies demonstrate that the proposed strategy reduces the economic cost and carbon emissions by 1%, and 0.5% compared to the single time‐scale strategy respectively.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139837582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel deep learning technique to detect electricity theft in smart grids using AlexNet 利用 AlexNet 检测智能电网中窃电行为的新型深度学习技术

IET Renewable Power Generation Pub Date : 2024-02-13 DOI: 10.1049/rpg2.12846

Nitasha Khan, Zeeshan Shahid, M. Alam, Aznida Abu Bakar Sajak, Mobeen Nazar, M. Mazliham

{"title":"A novel deep learning technique to detect electricity theft in smart grids using AlexNet","authors":"Nitasha Khan, Zeeshan Shahid, M. Alam, Aznida Abu Bakar Sajak, Mobeen Nazar, M. Mazliham","doi":"10.1049/rpg2.12846","DOIUrl":"https://doi.org/10.1049/rpg2.12846","url":null,"abstract":"Electricity theft (ET), which endangers public safety, interferes with the regular operation of grid infrastructure, and increases revenue losses, is a significant issue for power companies. To find ET, numerous machine learning, deep learning, and mathematically based algorithms have been published in the literature. However, these models do not yield the greatest results due to issues like the dimensionality curse, class imbalance, inappropriate hyper‐parameter tuning of machine learning, deep learning models etc. A hybrid DL model is presented for effectively detecting electricity thieves in smart grids while considering the abovementioned concerns. Pre‐processing techniques are first employed to clean up the data from the smart meters, and then the feature extraction technique, AlexNet is used to address the curse of dimensionality. An actual dataset of Chinese smart meters is used in simulations to assess the efficacy of the suggested approach. To conduct a comparative analysis, various benchmark models are implemented as well. This proposed model achieves accuracy, precision, recall, and F1‐score, up to 86%, 89%, 86%, and 84%, respectively.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"51 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139779688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An efficient, fast, and robust algorithm for single diode model parameters estimation of photovoltaic solar cells 光伏太阳能电池单二极管模型参数估计的高效、快速和稳健算法

IET Renewable Power Generation Pub Date : 2024-02-09 DOI: 10.1049/rpg2.12958

Husain A. Ismail, A. Diab

{"title":"An efficient, fast, and robust algorithm for single diode model parameters estimation of photovoltaic solar cells","authors":"Husain A. Ismail, A. Diab","doi":"10.1049/rpg2.12958","DOIUrl":"https://doi.org/10.1049/rpg2.12958","url":null,"abstract":"Parameter estimation of photovoltaic (PV) solar cells and module models pays attention to researchers owing to their importance in practical considerations. The single diode model (SDM) circuit with five unknown parameters is widely used to model PV solar cells and modules. In this paper, a novel approach called alternate optimization (AO) algorithm based on a discrete search is proposed to estimate the SDM parameters. The proposed algorithm provides efficient and robust performance, considering a limited set of discrete values and increasing the convergence speed. Two practical case studies with actual measurements are considered to assess the proposed AO algorithm: the RTC France solar cell and monocrystalline PV modules with different irradiations and temperatures. The numerical findings underscore the superior performance of the proposed AO algorithm across various metrics. Notably, it achieves an exceptional Root Mean Square Error (RMSE) of 7.7426 × 10−04 for the RTC France PV cell and approximately 1 × 10−03 RMSE for monocrystalline PV modules. Additionally, the algorithm exhibits unparalleled speed, showcasing the fastest convergence with an elapsed time of 1.66 × 10−05—markedly 4.45 times quicker than the fastest method documented in the literature for SDM parameter estimation. Furthermore, the proposed AO algorithm stands out for its efficiency, requiring a maximum of five iterations for parameter estimation, a substantial improvement compared to the more than 10 iterations typically needed by algorithms in the existing literature. Its robustness is also commendable, as evidenced by the stability of final RMSE values across a variety of experiments, distinguishing it from less robust algorithms found in the literature.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"410 30","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139848065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi‐objective multi‐period optimal site and size of distributed generation along with network reconfiguration 多目标多周期分布式发电的最佳地点和规模以及网络重组

IET Renewable Power Generation Pub Date : 2024-02-07 DOI: 10.1049/rpg2.12949

Ghulam Abbas, Zhi Wu, Aamir Ali

{"title":"Multi‐objective multi‐period optimal site and size of distributed generation along with network reconfiguration","authors":"Ghulam Abbas, Zhi Wu, Aamir Ali","doi":"10.1049/rpg2.12949","DOIUrl":"https://doi.org/10.1049/rpg2.12949","url":null,"abstract":"While extensive research has focused on enhancing distribution networks through either maximizing Distributed Generation (DG) integration or network reconfiguration at specific times, there is a need for further investigation into concurrently optimal network reconfiguration and DG allocation. To reduce the cost of energy delivered, the cost of energy loss, and voltage deviation, this study gives a dynamic multi‐objective network reconfiguration together with siting and sizing of dispatchable and non‐dispatchable DGs. The widely used IEEE 33‐bus and a large‐scale 118‐bus radial test system are employed while considering the time sequence fluctuations in sunlight irradiation and load. To address the pointed‐out challenge of multiperiod optimal DG allocation and reconfiguration while simultaneously decreasing the cost of energy supplied, the cost of energy lost, and the voltage deviation, a novel Multi‐objective Bidirectional co‐evolutionary algorithm (BiCo) is implemented. For better exploration and exploitation, the proposed algorithm integrating the constraint domination principle evolves the population from the feasible and infeasible search space with the help of a novel angle‐based density section. Simulation results demonstrate that the proposed approach outperforms previously published Multi‐objective Evolutionary Algorithms (MOEAs) by discovering a vast collection of uniformly spaced non‐dominated solutions in a single simulation run. Further, a fuzzy set theory is applied to find the best compromise solution among obtained final non‐dominated solutions. The results establish that the Pareto solutions significantly improved the system's voltage profile, with savings of over 22% compared to the baseline case and an exceptional improvement of over 80% in voltage deviation and power loss.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"55 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139857188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coordinated planning of DGs and soft open points in multi‐voltage level distributed networks based on the Stackelberg game 基于斯泰克尔伯格博弈的多电压等级分布式网络中风电机组和软开路点的协调规划

IET Renewable Power Generation Pub Date : 2024-02-07 DOI: 10.1049/rpg2.12963

Zhihua Chen, Ye He, Yuting Hua, Hongbin Wu, Rui Bi

{"title":"Coordinated planning of DGs and soft open points in multi‐voltage level distributed networks based on the Stackelberg game","authors":"Zhihua Chen, Ye He, Yuting Hua, Hongbin Wu, Rui Bi","doi":"10.1049/rpg2.12963","DOIUrl":"https://doi.org/10.1049/rpg2.12963","url":null,"abstract":"There are significant differences in distributed generators (DGs) distribution and load characteristics between different voltage levels, which makes it difficult to match sources and loads. We focus on the problem of different consumption capacities at different voltage levels and the divergence of interests among investment entities, and propose a coordinated planning model for DGs and soft open points (SOPs) based on the Stackelberg game. Firstly, a model of a multi‐voltage level distribution networks (DNs) is constructed based on SOPs. Next, the source‐load matching degree is proposed as a measure of the degree of matching between sources and loads in the DN, and the source‐load consumption rate is selected as an indicator to evaluate the impact of the load on DG consumption. Following this, the interest demands of DG investors and distribution company (DisCo) in multi‐voltage levels DN are analyzed, a planning mode based on the Stackelberg game is proposed, and this is solved by combining the genetic algorithm with second‐order cone programming. Finally, the effectiveness of the planning model is tested and verified using an improved IEEE 28‐node system. The results show that the proposed model improves the DG consumption capacity of DNs with multiple voltage levels while protecting the interests of DG investors and DisCo.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"26 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139795843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel wasserstein generative adversarial network for stochastic wind power output scenario generation 用于随机风电输出情景生成的新型 Wasserstein 生成式对抗网络

IET Renewable Power Generation Pub Date : 2024-02-01 DOI: 10.1049/rpg2.12932

Xiurong Zhang, Daoliang Li, Xueqian Fu

引用次数: 0

Hybrid model for wind power estimation based on BIGRU network and error discrimination‐correction 基于 BIGRU 网络和误差辨别校正的风能估算混合模型

IET Renewable Power Generation Pub Date : 2024-02-01 DOI: 10.1049/rpg2.12956

Yalong Li, Ye Jin, Yangqing Dan, Wenting Zha

{"title":"Hybrid model for wind power estimation based on BIGRU network and error discrimination‐correction","authors":"Yalong Li, Ye Jin, Yangqing Dan, Wenting Zha","doi":"10.1049/rpg2.12956","DOIUrl":"https://doi.org/10.1049/rpg2.12956","url":null,"abstract":"Accurate estimation of wind power is essential for predicting and maintaining the power balance in the power system. This paper proposes a novel approach to enhance the accuracy of wind power estimation through a hybrid model integrating neural networks and error discrimination‐correction techniques. In order to improve the accuracy of estimation, a bidirectional gating recurrent unit is developed, forming an initial wind power estimation curve through training. Additionally, a sequential model‐based algorithmic configuration optimizes bidirectional gating recurrent unit's network hyperparameters. To tackle estimation errors, a multi‐layer perceptron combined with sequential model‐based algorithmic configuration is employed to create a classification model that automatically discerns the quality of estimates. Subsequently, an innovative correction model, based on grey relevancy degree and relevancy errors, is devised to rectify erroneous estimates. The final estimates result from a summation of the initial estimates and the values derived from error corrections. By analysing the real data from a wind farm in northwest China, a simulation test validates the proposed hybrid model. Experimental results demonstrate a substantial improvement in modelling accuracy when compared to the initial model.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"77 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139824675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel DC‐link voltage synchronous control with enhanced inertial capability for full‐scale power conversion wind turbine generators 用于全功率转换风力涡轮发电机的具有增强惯性能力的新型直流链路电压同步控制装置

IET Renewable Power Generation Pub Date : 2024-02-01 DOI: 10.1049/rpg2.12936

Yao Qin, Han Wang, Dangsheng Zhou, Zhen-Quan Deng, Jianwen Zhang, Xu Cai

{"title":"A novel DC‐link voltage synchronous control with enhanced inertial capability for full‐scale power conversion wind turbine generators","authors":"Yao Qin, Han Wang, Dangsheng Zhou, Zhen-Quan Deng, Jianwen Zhang, Xu Cai","doi":"10.1049/rpg2.12936","DOIUrl":"https://doi.org/10.1049/rpg2.12936","url":null,"abstract":"The new power system is characterized by high penetration of renewable energy sources and a high proportion of power electronics (namely, double‐high). The grid‐forming control is an effective method to improve the grid‐connected stability of wind turbine generators (WTGs) in the “double‐high” grid. The control method based on the DC‐link voltage can effectively realize the grid‐forming control for WTGs. However, there is a disadvantage that the DC‐link voltage cannot be maintained at the given value. To address this, the grid synchronization mechanism of DC‐link voltage is explored and the specific implementation of a novel DC‐link voltage synchronous control applicable to full‐scale power conversion WTGs is proposed. Then, the boundary of the inertial coefficient is probed through the state‐space method. And a compensation control is proposed to enlarge the inertial response capability based on the mechanism of damping characteristics. Finally, the PSCAD/EMTDC simulation and RTLAB hardware‐in‐loop experiment show that the synchronization frequency can accurately map the grid frequency changes in real‐time under the premise that the DC‐link voltage remains constant. In addition, the inertial coefficient can be increased by more than five times with the compensation strategy, which can enhance the support capability of the WTGs to the power grid.","PeriodicalId":507938,"journal":{"name":"IET Renewable Power Generation","volume":"361 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139828318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0