Scholarlink

<p>The rising switch to renewable energy resources and the energy mix in case of power grid demands technological upgradation so as to continue with the unintermittent supply of electricity. A residential grid, it consists of multiple homes, each with different members and behavioral attributes. The demand side management strategies implemented on a residential grid modify the electricity consumption behavior in order to maintain an equilibrium between demand and supply of electricity. The consumers in return receive several incentives that further motivate them to participate in such programs. Due to the diverse consumer set involved in DSM operations, providing incentives can be challenging and costly for utilities to manage. Also, the DSM operations run at the risk of failure when the consumers opt out from the program because their comfort is compromised as a result of the load shift. In this regard, this paper aims to classify the consumers based on their suitability for DSM operations. Based on the historic consumption behavior of the consumers, the proposed classification framework finds potential targets who can help in a significant amount of load reduction as a result of DSM operations. The framework creates a graph structure from the historic load consumption data of each residential home which is then used to train the GCN classifier model to classify the residential home for their suitability. The DSM-GCN framework is trained on Ireland residential grid with half hourly electricity consumption data of more than an year. A comparative analysis is performed with some of the baseline classifier models and the DSM based models. The predicted set of residential homes show an overall decrease in load consumption of upto <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41060_2025_735_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(10\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>10</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A classification framework for demand side management in residential smart grids

  • 期刊论文

  • 发表日期：

    2025年3月12日

查看全文
  • Kakuli Mishra,
  • Srinka Basu,
  • Ujjwal Maulik

摘要

The rising switch to renewable energy resources and the energy mix in case of power grid demands technological upgradation so as to continue with the unintermittent supply of electricity. A residential grid, it consists of multiple homes, each with different members and behavioral attributes. The demand side management strategies implemented on a residential grid modify the electricity consumption behavior in order to maintain an equilibrium between demand and supply of electricity. The consumers in return receive several incentives that further motivate them to participate in such programs. Due to the diverse consumer set involved in DSM operations, providing incentives can be challenging and costly for utilities to manage. Also, the DSM operations run at the risk of failure when the consumers opt out from the program because their comfort is compromised as a result of the load shift. In this regard, this paper aims to classify the consumers based on their suitability for DSM operations. Based on the historic consumption behavior of the consumers, the proposed classification framework finds potential targets who can help in a significant amount of load reduction as a result of DSM operations. The framework creates a graph structure from the historic load consumption data of each residential home which is then used to train the GCN classifier model to classify the residential home for their suitability. The DSM-GCN framework is trained on Ireland residential grid with half hourly electricity consumption data of more than an year. A comparative analysis is performed with some of the baseline classifier models and the DSM based models. The predicted set of residential homes show an overall decrease in load consumption of upto \(10\%\) 10 % .