{"title":"用于微电网经济调度的物理信息卷积神经网络","authors":"Xiaoyu Ge, Javad Khazaei","doi":"10.1016/j.segan.2024.101525","DOIUrl":null,"url":null,"abstract":"<div><p>The variability of renewable energy generation and the unpredictability of electricity demand create a need for real-time economic dispatch (ED) of assets in microgrids. However, solving numerical optimization problems in real-time can be incredibly challenging. This study proposes using a convolutional neural network (CNN) based on deep learning to address these challenges. Compared to traditional methods, CNN is more efficient, delivers more dependable results, and has a shorter response time when dealing with uncertainties. While CNN has shown promising results, it does not extract explainable knowledge from the data. To address this limitation, a physics-inspired CNN model is developed by incorporating constraints of the ED problem into the CNN training to ensure that the model follows physical laws while fitting the data. The proposed method can significantly accelerate real-time economic dispatch of microgrids without compromising the accuracy of numerical optimization techniques. The effectiveness of the proposed data-driven approach for optimal allocation of microgrid resources in real-time is verified through a comprehensive comparison with conventional numerical optimization approaches.</p></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"40 ","pages":"Article 101525"},"PeriodicalIF":4.8000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Physics-informed convolutional neural network for microgrid economic dispatch\",\"authors\":\"Xiaoyu Ge, Javad Khazaei\",\"doi\":\"10.1016/j.segan.2024.101525\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The variability of renewable energy generation and the unpredictability of electricity demand create a need for real-time economic dispatch (ED) of assets in microgrids. However, solving numerical optimization problems in real-time can be incredibly challenging. This study proposes using a convolutional neural network (CNN) based on deep learning to address these challenges. Compared to traditional methods, CNN is more efficient, delivers more dependable results, and has a shorter response time when dealing with uncertainties. While CNN has shown promising results, it does not extract explainable knowledge from the data. To address this limitation, a physics-inspired CNN model is developed by incorporating constraints of the ED problem into the CNN training to ensure that the model follows physical laws while fitting the data. The proposed method can significantly accelerate real-time economic dispatch of microgrids without compromising the accuracy of numerical optimization techniques. The effectiveness of the proposed data-driven approach for optimal allocation of microgrid resources in real-time is verified through a comprehensive comparison with conventional numerical optimization approaches.</p></div>\",\"PeriodicalId\":56142,\"journal\":{\"name\":\"Sustainable Energy Grids & Networks\",\"volume\":\"40 \",\"pages\":\"Article 101525\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sustainable Energy Grids & Networks\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352467724002546\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Energy Grids & Networks","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352467724002546","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
摘要
可再生能源发电的多变性和电力需求的不可预测性,使得微电网中的资产需要进行实时经济调度(ED)。然而,实时求解数值优化问题具有极大的挑战性。本研究建议使用基于深度学习的卷积神经网络(CNN)来应对这些挑战。与传统方法相比,卷积神经网络更高效、结果更可靠,而且在处理不确定性时响应时间更短。虽然 CNN 已显示出良好的效果,但它无法从数据中提取可解释的知识。为解决这一局限性,我们开发了一种受物理学启发的 CNN 模型,将 ED 问题的约束条件纳入 CNN 训练,以确保模型在拟合数据时遵循物理规律。所提出的方法可以大大加快微电网的实时经济调度,同时不影响数值优化技术的准确性。通过与传统数值优化方法的综合比较,验证了所提出的数据驱动方法在微电网资源实时优化分配方面的有效性。
Physics-informed convolutional neural network for microgrid economic dispatch
The variability of renewable energy generation and the unpredictability of electricity demand create a need for real-time economic dispatch (ED) of assets in microgrids. However, solving numerical optimization problems in real-time can be incredibly challenging. This study proposes using a convolutional neural network (CNN) based on deep learning to address these challenges. Compared to traditional methods, CNN is more efficient, delivers more dependable results, and has a shorter response time when dealing with uncertainties. While CNN has shown promising results, it does not extract explainable knowledge from the data. To address this limitation, a physics-inspired CNN model is developed by incorporating constraints of the ED problem into the CNN training to ensure that the model follows physical laws while fitting the data. The proposed method can significantly accelerate real-time economic dispatch of microgrids without compromising the accuracy of numerical optimization techniques. The effectiveness of the proposed data-driven approach for optimal allocation of microgrid resources in real-time is verified through a comprehensive comparison with conventional numerical optimization approaches.
期刊介绍:
Sustainable Energy, Grids and Networks (SEGAN)is an international peer-reviewed publication for theoretical and applied research dealing with energy, information grids and power networks, including smart grids from super to micro grid scales. SEGAN welcomes papers describing fundamental advances in mathematical, statistical or computational methods with application to power and energy systems, as well as papers on applications, computation and modeling in the areas of electrical and energy systems with coupled information and communication technologies.