基于SSA-ELM混合模型的光伏出力预测

打开文本图片集

中图分类号：TM615 文献标志码：A 文章编号：2095-2945（2025）25-0058-04

Abstract：Thehighaspectratiodistributedphotovoltaicgridconnection hasbroughtabout manyproblems.Acurateand reliablephotovoltaicoutputpredictionisthefoundationforimprovingthepenetrationrateofhighaspectratiodistributed photovoltaicdistributionnetworkadjustmentandcontrolcapabilities.Therefore，startingfromngineringusabilitythispaper selectstherelativelyeasytoimplementExtremeLearning Machine（ELM）tocarryoutphotovoltaicoutputpredictionInorderto aleviate heproblemoflowpredictionacuracycausedbytherandomnessofELMweightsandbiases，thispaperusesSparrow IntellgentAlgorithmtooptimizeELMweightsandbiases.TheexperimentalresultsshowthatcomparedwiththeoriginalELM， theerrorofthepredictionmodelusedinthispaperisreducedbyhalf，efectivelyimprovingtheaccuracyofphotovoltaicoutput prediction.

Keywords：distributedphotovoltaic;distributionnetwork;ExtremeLearningMachine（ELM）；SparrowSearchAlgorithm（SA）; accuracy

为了缓解全球气候恶化及化石能源逐渐枯竭等问题，我国甚至全球均在推进以可再生能源为主体的新型电力系统建设，而高比例新能源配电网是新型电力系统的主要特征之一，然而由于分布式光伏出力具有间隙性和随机性，其对配电网冲击越来越明显。（剩余5008字）