摘要
短期分布式光伏发电功率预测对配电网调度计划的安排及优化具有重要意义。人工智能技术的进步为精细化分析光伏发电功率预测结果的影响因素以及提高光伏发电功率的预测精度提供了有效途径。文章提出一种基于特征筛选与ANFIS-PSO的分布式光伏发电功率预测方法。首先,基于随机森林中的增益情况,对影响分布式光伏发电系统的各项特征参数进行筛选;然后,通过自适应神经模糊推理算法对输入数据进行训练,并使用粒子群算法对ANFIS模型进行优化;接着,建立基于离线训练和在线预测的ANFIS-PSO分布式光伏发电功率预测模型;最后,利用北京某地分布式光伏发电系统的实际数据来验证模拟结果的准确性。
Accurate short-term distributed photovoltaic(PV) generation forecasting is very important for the dispatching of power system and optimal operation of PV system. The progress of machine learning and artificial intelligence technology provides an effective way for further analysis of PV power prediction factors and improving forecasting accuracy. A short-term photovoltaic power forecasting method based on feature selection and ANFIS-PSO is proposed in this paper. Firstly, considering that the gains in the random forest, the features are selected from input information, the mechanism of adaptive neuro-fuzzy inference system, random forest algorithm and particle swarm optimization method are introduced. Then, the short-term distributed photovoltaic power forecasting model of ANFIS-PSO based on off-line training and on-line forecasting is established. At last, algorithm validity and accuracy of power forecast approach for PV system are verified by the simulation using actual operating data of PV system.
作者
时珉
王强
王铁强
王一峰
尹瑞
何琰
Yordanos Kassa Semero
Shi Min;Wang Qiang;Wang Tieqiang;Wang Yifeng;Yin Rui;He Yan;Yordanos Kassa Semero(State Grid Hebei Electric Power Co.,Ltd.,Shijiazhuang 050021,China;Beijing Tsingsoft Innovation Technology Co.,Ltd.,Beijing 100085,China;State Key Laboratory of Alternative Electrical Power System With Renewable Energy Sources,North China Electric Power University,Beijing 102206,China)
出处
《可再生能源》
CAS
北大核心
2019年第7期989-994,共6页
Renewable Energy Resources
基金
国家自然科学基金(51507061)
国家重点研发计划项目(2017YFB0903100)
关键词
分布式光伏发电系统
发电功率预测
特征筛选
自适应神经模糊推理算法
粒子群算法
short-term distributed PV
generation forecasting
adaptive neuro-fuzzy inference system
particle swarm optimization
feature selection
