{"title":"利用基于 GRU 控制器的能源管理系统降低多功能微电网的成本消耗并管理电力流","authors":"Harini Vaikund, S. G. Srivani","doi":"10.1007/s00202-024-02605-3","DOIUrl":null,"url":null,"abstract":"<p>The demand for energy on the global is rising quickly, and the majority of that demand is met by the production of traditional fossil fuels. An original idea for incorporating renewable and hybrid energy sources to a grid was known as microgrid model. For proper power sharing between each component in the microgrid to ensure efficient, dependable, and cost-effective operation, Energy Management Systems (EMS) were crucial in microgrids through multiple energy resources and storage systems. Improper source prediction at the appropriate period was the issue that occurred in the EMS. This problem with efficiency causes a number of power-related issues on the load side and raises electricity costs. To mitigate this impacts, a novel deep learning controller-based EMS was proposed to manage the power flows at all period and reduce the cost of end users. Minimization of microgrid total electricity cost and total annual emission were considered as the primary objectives of the proposed model. Microgrid was designed with PV, tidal, grid, and battery, and in the demand side both hospital and home usages were considered. An actual dataset was developed according to the load activation power demand with its corresponding source power cost. Using this dataset, the deep learning controller was designed, and its performance was further improved through the coati optimization algorithm. The designed controller was fit in the EMS to select the proper source at the appropriate load demand period. The working states of the proposed model were observed under grid linked, and grid disliked mode of operation. The proposed deep learning controller offers 99.7% accuracy and 99.5% precision, and the results were compared to several other existing approaches. The outcomes demonstrate that the deep learning EMS approach was capable of interacting with many power sources and offer effective power management at a reasonable cost.</p>","PeriodicalId":50546,"journal":{"name":"Electrical Engineering","volume":"161 1","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Mitigation of cost consumption and manage power flows in multi-purpose microgrid using GRU controller-based energy management system\",\"authors\":\"Harini Vaikund, S. G. Srivani\",\"doi\":\"10.1007/s00202-024-02605-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The demand for energy on the global is rising quickly, and the majority of that demand is met by the production of traditional fossil fuels. An original idea for incorporating renewable and hybrid energy sources to a grid was known as microgrid model. For proper power sharing between each component in the microgrid to ensure efficient, dependable, and cost-effective operation, Energy Management Systems (EMS) were crucial in microgrids through multiple energy resources and storage systems. Improper source prediction at the appropriate period was the issue that occurred in the EMS. This problem with efficiency causes a number of power-related issues on the load side and raises electricity costs. To mitigate this impacts, a novel deep learning controller-based EMS was proposed to manage the power flows at all period and reduce the cost of end users. Minimization of microgrid total electricity cost and total annual emission were considered as the primary objectives of the proposed model. Microgrid was designed with PV, tidal, grid, and battery, and in the demand side both hospital and home usages were considered. An actual dataset was developed according to the load activation power demand with its corresponding source power cost. Using this dataset, the deep learning controller was designed, and its performance was further improved through the coati optimization algorithm. The designed controller was fit in the EMS to select the proper source at the appropriate load demand period. The working states of the proposed model were observed under grid linked, and grid disliked mode of operation. The proposed deep learning controller offers 99.7% accuracy and 99.5% precision, and the results were compared to several other existing approaches. The outcomes demonstrate that the deep learning EMS approach was capable of interacting with many power sources and offer effective power management at a reasonable cost.</p>\",\"PeriodicalId\":50546,\"journal\":{\"name\":\"Electrical Engineering\",\"volume\":\"161 1\",\"pages\":\"\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electrical Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s00202-024-02605-3\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electrical Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s00202-024-02605-3","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Mitigation of cost consumption and manage power flows in multi-purpose microgrid using GRU controller-based energy management system
The demand for energy on the global is rising quickly, and the majority of that demand is met by the production of traditional fossil fuels. An original idea for incorporating renewable and hybrid energy sources to a grid was known as microgrid model. For proper power sharing between each component in the microgrid to ensure efficient, dependable, and cost-effective operation, Energy Management Systems (EMS) were crucial in microgrids through multiple energy resources and storage systems. Improper source prediction at the appropriate period was the issue that occurred in the EMS. This problem with efficiency causes a number of power-related issues on the load side and raises electricity costs. To mitigate this impacts, a novel deep learning controller-based EMS was proposed to manage the power flows at all period and reduce the cost of end users. Minimization of microgrid total electricity cost and total annual emission were considered as the primary objectives of the proposed model. Microgrid was designed with PV, tidal, grid, and battery, and in the demand side both hospital and home usages were considered. An actual dataset was developed according to the load activation power demand with its corresponding source power cost. Using this dataset, the deep learning controller was designed, and its performance was further improved through the coati optimization algorithm. The designed controller was fit in the EMS to select the proper source at the appropriate load demand period. The working states of the proposed model were observed under grid linked, and grid disliked mode of operation. The proposed deep learning controller offers 99.7% accuracy and 99.5% precision, and the results were compared to several other existing approaches. The outcomes demonstrate that the deep learning EMS approach was capable of interacting with many power sources and offer effective power management at a reasonable cost.
期刊介绍:
The journal “Electrical Engineering” following the long tradition of Archiv für Elektrotechnik publishes original papers of archival value in electrical engineering with a strong focus on electric power systems, smart grid approaches to power transmission and distribution, power system planning, operation and control, electricity markets, renewable power generation, microgrids, power electronics, electrical machines and drives, electric vehicles, railway electrification systems and electric transportation infrastructures, energy storage in electric power systems and vehicles, high voltage engineering, electromagnetic transients in power networks, lightning protection, electrical safety, electrical insulation systems, apparatus, devices, and components. Manuscripts describing theoretical, computer application and experimental research results are welcomed.
Electrical Engineering - Archiv für Elektrotechnik is published in agreement with Verband der Elektrotechnik Elektronik Informationstechnik eV (VDE).