中国电机工程学报
中國電機工程學報
중국전궤공정학보
ZHONGGUO DIANJI GONGCHENG XUEBAO
2014年
34期
6032-6041
,共10页
刘昇%徐政%华文%黄弘扬
劉昇%徐政%華文%黃弘颺
류승%서정%화문%황홍양
静态电压稳定%神经网络%在线%电网状态相似度%最小绝对值收缩选择
靜態電壓穩定%神經網絡%在線%電網狀態相似度%最小絕對值收縮選擇
정태전압은정%신경망락%재선%전망상태상사도%최소절대치수축선택
static voltage stability%neural network%online%similarity index of power system state (SIPSS)%least absolute shrinkage and select operator (Lasso)
快速求解系统负荷能力极限是在线评估电力系统电压稳定性的基本要求。提出一种用于离线拟合并在线预测负荷能力极限的 SIPSS-Lasso-BP 网络。该网络由基于电网状态相似度指标(similarity index of power system state,SIPSS)的样本筛选方法、最小绝对值收缩选择(least absolute shrinkage and select operator,Lasso)方法和BP(back propagation)神经网络共同组成。基于SIPSS的样本筛选方法以样本负荷能力极限值和电网状态相似度量化指标为依据,对训练样本进行筛选。Lasso 方法对训练样本进行回归分析,确定各状态量中对负荷能力极限最具有解释性的系统状态量。BP神经网络通过精简后的训练样本来离线拟合负荷能力极限并用于在线预测。通过新英格兰39节点算例和某省实际算例对SIPSS-Lasso-BP网络的测试结果表明,该方法能够在保证预测精度的情况下明显提高 BP 神经网络的离线训练效率。
快速求解繫統負荷能力極限是在線評估電力繫統電壓穩定性的基本要求。提齣一種用于離線擬閤併在線預測負荷能力極限的 SIPSS-Lasso-BP 網絡。該網絡由基于電網狀態相似度指標(similarity index of power system state,SIPSS)的樣本篩選方法、最小絕對值收縮選擇(least absolute shrinkage and select operator,Lasso)方法和BP(back propagation)神經網絡共同組成。基于SIPSS的樣本篩選方法以樣本負荷能力極限值和電網狀態相似度量化指標為依據,對訓練樣本進行篩選。Lasso 方法對訓練樣本進行迴歸分析,確定各狀態量中對負荷能力極限最具有解釋性的繫統狀態量。BP神經網絡通過精簡後的訓練樣本來離線擬閤負荷能力極限併用于在線預測。通過新英格蘭39節點算例和某省實際算例對SIPSS-Lasso-BP網絡的測試結果錶明,該方法能夠在保證預測精度的情況下明顯提高 BP 神經網絡的離線訓練效率。
쾌속구해계통부하능력겁한시재선평고전력계통전압은정성적기본요구。제출일충용우리선의합병재선예측부하능력겁한적 SIPSS-Lasso-BP 망락。해망락유기우전망상태상사도지표(similarity index of power system state,SIPSS)적양본사선방법、최소절대치수축선택(least absolute shrinkage and select operator,Lasso)방법화BP(back propagation)신경망락공동조성。기우SIPSS적양본사선방법이양본부하능력겁한치화전망상태상사도양화지표위의거,대훈련양본진행사선。Lasso 방법대훈련양본진행회귀분석,학정각상태량중대부하능력겁한최구유해석성적계통상태량。BP신경망락통과정간후적훈련양본래리선의합부하능력겁한병용우재선예측。통과신영격란39절점산례화모성실제산례대SIPSS-Lasso-BP망락적측시결과표명,해방법능구재보증예측정도적정황하명현제고 BP 신경망락적리선훈련효솔。
Solving loadability limit quickly is the basic requirement of online assessment for power systems voltage stability. This paper proposed a SIPSS-Lasso-BP network aiming to offline fitting and online forecasting the loadability limit. The network consisted of the similarity index of power system state (SIPSS) based screening method, the least absolute shrinkage and select operator (Lasso) algorithm and the back propagation (BP) neural network. The SIPSS based screening method screened the training samples according to their loadability limits and similarity indexes of power system state. The Lasso algorithm selected the principal system state variables which were most explanatory to the loadability limit via the modified regression analysis of the training samples. The BP network was used to offline fit and online forecast the loadability limit of the system through the cut training samples. The test results on the New England 39-bus system and a practical example show that the SIPSS-Lasso-BP network can significantly improve the efficiency of offline training the BP network and guarantee the forecasting accuracy.