基于DAG-SVMS的非侵入式負荷識別方法
2021年電子技術應用第10期
王 毅1,2,徐元源1,李松濃2
1.重慶郵電大學 通信與信息工程學院,重慶400065;2.國網重慶市電力公司電力科學研究院,重慶404100
摘要: 在供電入口處嵌入非侵入式負荷識別技術,有利于推動建筑節能、實現電網負荷預測、開發智能樓宇、完善智能電網體系建設。據此,提出一種基于有向無環圖支持向量機(Directed Acyclic Graph Support Vector Machines,DAG-SVMS)的負荷辨識方法。首先,對總線電流信號進行事件檢測,檢測到暫態事件后,分離目標負荷暫態電流波形,提取特征,然后,將特征輸入預先訓練好的DAG-SVMS模型進行分類識別。為提升分類器性能,使用粒子群優化PSO(Particle Swarm Optimization)算法優化DAG-SVMS分類器的參數。為減小累積誤差,提出Gini指數優化DAG-SVMS節點順序的策略。實驗結果表明,文中方法識別準確率高,識別速度快,具有可行性。
中圖分類號: TN915
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.211451
中文引用格式: 王毅,徐元源,李松濃. 基于DAG-SVMS的非侵入式負荷識別方法[J].電子技術應用,2021,47(10):107-112.
英文引用格式: Wang Yi,Xu Yuanyuan,Li Songnong. Non-intrusive load identification method based on improved directed acyclic graph support vector machines[J]. Application of Electronic Technique,2021,47(10):107-112.
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.211451
中文引用格式: 王毅,徐元源,李松濃. 基于DAG-SVMS的非侵入式負荷識別方法[J].電子技術應用,2021,47(10):107-112.
英文引用格式: Wang Yi,Xu Yuanyuan,Li Songnong. Non-intrusive load identification method based on improved directed acyclic graph support vector machines[J]. Application of Electronic Technique,2021,47(10):107-112.
Non-intrusive load identification method based on improved directed acyclic graph support vector machines
Wang Yi1,Xu Yuanyuan1,Li Songnong2
1.School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications, Chongqing 400065,China; 2.Chongqing Electric Power Research Institute,Chongqing 404100,China
Abstract: Embedding non-intrusive load identification technology in the power supply entrance is conducive to promote building energy saving, realize power grid load forecasting, develop intelligent buildings and improve the construction of smart grid system. Therefore, this paper proposes a non-intrusive power load identification method based on directed acyclic graph support vector machines(DAG-SVMS). Firstly, the event detection of power system bus current signal is carried out. After the transient event is detected, the transient current waveform of the target load is separated and the features are extracted. Then, the features are input into the pre trained DAG-SVMS model for classification and identification. In order to improve the performance of the classifier, particle awarm optimization(PSO) algorithm is used to optimize the parameters of the DAG-SVMS model. In order to reduce the cumulative error, Gini index is proposed to optimize the node order of DAG-SVMS. The experimental results show that the proposed method has high recognition accuracy, fast recognition speed and feasibility.
Key words : non-intrusive load identification;transient event;DAG-SVMS model;Gini index;PSO algorithm
0 引言
智能電網建設是以提高生態可持續性、供電安全性和經濟競爭力為目標[1],表現為提高負荷監測技術、提高終端用戶響應速度、提高需求側的節約能效、提供智能控制技術、分布式能源的自由接入[2]。非侵入式負荷識別作為非侵入式負荷監測的核心內容,在不改變用戶電路結構的條件下,通過測量總負荷數據,即可獲得系統內具體用電負荷的數量、類別、運行狀態信息,安裝和維護成本低,易于推廣。該技術的實現,可為用戶、電力公司以及設備提供參考[3]。用戶端,用戶用電信息得到反饋,提升節能意識,規范用電行為。電力公司端,能提高負荷預測的精確度,實現有效的負荷規劃、電能調度。對設備制造商來說,可據此識別出故障或低效設備,加快技術革新,推動高能效設備研發。
本文詳細內容請下載:http://m.viuna.cn/resource/share/2000003793。
作者信息:
王 毅1,2,徐元源1,李松濃2
(1.重慶郵電大學 通信與信息工程學院,重慶400065;2.國網重慶市電力公司電力科學研究院,重慶404100)
此內容為AET網站原創,未經授權禁止轉載。