《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 人工智能 > 設(shè)計(jì)應(yīng)用 > 計(jì)及可再生能源接入配電網(wǎng)的負(fù)荷預(yù)測(cè)和優(yōu)化
計(jì)及可再生能源接入配電網(wǎng)的負(fù)荷預(yù)測(cè)和優(yōu)化
電子技術(shù)應(yīng)用
翟哲1,余杰文2,杜洋3,曹澤江4
1.中國南方電網(wǎng)電力調(diào)度控制中心;2.南方電網(wǎng)人工智能科技有限公司; 3.深圳市法本信息技術(shù)股份有限公司;4.南方電網(wǎng)數(shù)字電網(wǎng)科技(廣東)有限公司
摘要: 目前,可再生能源大量接入配電網(wǎng),但是太陽能、風(fēng)能、光伏及風(fēng)電等可再生能源的間歇性和隨機(jī)性不可避免地會(huì)造成配電網(wǎng)的波動(dòng)。考慮電網(wǎng)內(nèi)可再生能源發(fā)電功率與用電負(fù)荷隨時(shí)間變化的特點(diǎn),提出一種基于小波變換和神經(jīng)網(wǎng)絡(luò)的可再生能源接入配電網(wǎng)的負(fù)荷預(yù)測(cè)和優(yōu)化方法。首先采集配電網(wǎng)的發(fā)電與負(fù)荷數(shù)據(jù),利用小波變換處理收集到的數(shù)據(jù),得到局部尺度和頻率分解的特征參數(shù),建立神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型;然后,對(duì)經(jīng)過小波變換后得到的特征參數(shù)進(jìn)行訓(xùn)練,根據(jù)預(yù)測(cè)負(fù)荷對(duì)可再生能源的發(fā)電量進(jìn)行調(diào)節(jié),保持配電網(wǎng)供需側(cè)的動(dòng)態(tài)平衡。結(jié)果表明,所提方法能夠?qū)ω?fù)荷進(jìn)行有效預(yù)測(cè),通過提前預(yù)測(cè)負(fù)荷量,保證配電網(wǎng)用電穩(wěn)定性的同時(shí),最大化利用可再生能源。
中圖分類號(hào):TM93 文獻(xiàn)標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.245284
中文引用格式: 翟哲,余杰文,杜洋,等. 計(jì)及可再生能源接入配電網(wǎng)的負(fù)荷預(yù)測(cè)和優(yōu)化[J]. 電子技術(shù)應(yīng)用,2024,50(11):35-41.
英文引用格式: Zhai Zhe,Yu Jiewen,Du Yang,et al. Load prediction and optimization of renewable energy access to the distribution network[J]. Application of Electronic Technique,2024,50(11):35-41.
Load prediction and optimization of renewable energy access to the distribution network
Zhai Zhe1,Yu Jiewen2,Du Yang3,Cao Zejiang4
1.Dispatching and Control Center, China Southern Power Grid; 2.China Southern Power Grid Artificial Intelligence Technology Co., Ltd.; 3.Shenzhen Faben Information Technology Co., Ltd.; 4.China Southern Power Grid Digital Power Grid Technology (Guangdong) Co., Ltd.
Abstract: Currently, with the large-scale integration of renewable energy into the distribution network, the intermittency and randomness of renewable energy sources such as solar and wind power inevitably cause fluctuations in the distribution network. Considering the characteristics of renewable energy generation power and electricity load in the power grid over time, a load prediction and optimization method based on wavelet transform and neural network for renewable energy access to the distribution network is proposed. Firstly, the grid operation data are collected, and the wavelet transform is used to process the collected data to obtain the feature parameters of local scale and frequency decomposition. A neural network is established. Then the feature parameters obtained after the wavelet transform are trained to obtain a model capable of predicting the load, according to which the power generation of renewable energy sources can be adjusted in time to maintain the dynamic balance between the supply and demand sides of the distribution network. The results show that the proposed method can effectively predict the load and regulate the power generation by observing the load in advance to ensure the stability of power consumption in the distribution network and simultaneously maximize the use of renewable energy.
Key words : cloud technology;neural network;wavelet transform;wind and solar power generation;load prediction;power generation optimization

引言

近年來,可再生能源發(fā)電設(shè)備裝機(jī)容量持續(xù)增長,極大地提升了配電網(wǎng)滿足更多用電負(fù)荷的能力[1]。但是風(fēng)光發(fā)電出力波動(dòng)性大,對(duì)電力系統(tǒng)的運(yùn)行方式、潮流方向及電網(wǎng)運(yùn)行態(tài)勢(shì)造成了很大的影響,提升了調(diào)度難度[2-3]。目前,解決可再生能源波動(dòng)性對(duì)電網(wǎng)用電穩(wěn)定性的影響的需求不斷增強(qiáng)。在此背景下,張耀聰[4]利用LSTM、注意力機(jī)制的神經(jīng)網(wǎng)絡(luò)對(duì)風(fēng)力、太陽能等可再生能源的出力進(jìn)行預(yù)測(cè)以優(yōu)化電網(wǎng)調(diào)度方式;葉梁勁等人[5]利用小波變換對(duì)電力負(fù)荷相關(guān)數(shù)據(jù)(天氣、日期等)進(jìn)行特征提取,使用LSTM長短期記憶神經(jīng)網(wǎng)絡(luò)對(duì)特征提取后的數(shù)據(jù)進(jìn)行訓(xùn)練,以實(shí)現(xiàn)對(duì)電力系統(tǒng)的負(fù)荷預(yù)測(cè),得到了較高精度的預(yù)測(cè)模型;楊麗薇等人[6]采用小波分解與BP神經(jīng)網(wǎng)絡(luò)的組合算法,預(yù)測(cè)相同天氣類型下的光伏電站短期功率輸出,實(shí)現(xiàn)了對(duì)晴天與多云天氣下的光伏功率輸出預(yù)測(cè)。預(yù)測(cè)態(tài)勢(shì)感知技術(shù)也逐漸被用于優(yōu)化配電網(wǎng)的運(yùn)行過程[7-9]。

雖然不少研究學(xué)者針對(duì)電力負(fù)荷預(yù)測(cè)做出了研究并得到了一定研究成果,但目前的研究缺乏一套可以執(zhí)行的系統(tǒng),并且研究對(duì)象(數(shù)據(jù)集的參量)較為單一。綜上所述,針對(duì)現(xiàn)有研究難以解決風(fēng)光發(fā)電波動(dòng)大、負(fù)荷大小難以預(yù)測(cè)對(duì)電網(wǎng)運(yùn)行態(tài)勢(shì)造成重大影響以及調(diào)度困難的問題,本文通過構(gòu)建配電網(wǎng)態(tài)勢(shì)感知框架,提出了一種基于小波變換和神經(jīng)網(wǎng)絡(luò)的可再生能源接入配電網(wǎng)的負(fù)荷預(yù)測(cè)和優(yōu)化方法。首先,采集電網(wǎng)運(yùn)行數(shù)據(jù),利用小波變換處理收集到的數(shù)據(jù),得到局部尺度和頻率分解的特征參數(shù);然后建立神經(jīng)網(wǎng)絡(luò),對(duì)經(jīng)過小波變換后得到的特征參數(shù)進(jìn)行訓(xùn)練,得到能夠預(yù)測(cè)負(fù)荷的模型,通過預(yù)測(cè)負(fù)荷并結(jié)合實(shí)時(shí)用電需求進(jìn)行合理的調(diào)度,實(shí)現(xiàn)發(fā)電設(shè)備與用電設(shè)備的之間的平衡,提高配電網(wǎng)的穩(wěn)定性;最后運(yùn)用至實(shí)例中表明,本文方法能夠在保證最大化利用綠色可再生能源的同時(shí),維持用戶側(cè)的用電穩(wěn)定,提升含有可再生能源的配電網(wǎng)可靠性。


本文詳細(xì)內(nèi)容請(qǐng)下載:

http://ihrv.cn/resource/share/2000006207


作者信息:

翟哲1,余杰文2,杜洋3,曹澤江4

(1.中國南方電網(wǎng)電力調(diào)度控制中心,廣東 廣州 510000;

2.南方電網(wǎng)人工智能科技有限公司,廣東 廣州 510000;

3.深圳市法本信息技術(shù)股份有限公司,廣東 廣州 510000;

4.南方電網(wǎng)數(shù)字電網(wǎng)科技(廣東)有限公司,廣東 廣州 510000)


Magazine.Subscription.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。