Clustering and Simulation of Photovoltaic Output Adopting Markov Model

doi:10.3969/j.issn.1000-7229.2019.02.007

Abstract

Abstract: Processing data properly and constructing a rational photovoltaic output model is the base of power system operation and plan. Focusing on characteristics of photovoltaic output， a photovoltaic output clustering and simulation method based on Markov model and spectral clustering is proposed. Firstly， the amplitude parameter， the standard component and fluctuant component are extracted from photovoltaic output and Markov model is adopted to analyze the fluctuant component. We use spectral clustering and Alpha value， Silhouette index and Bayesian information criterion to evaluate the quality of clustering results and to determine the optimal cluster number. Then， state-transition matrixes between the weather in the month and power output in the day are integrated， and a bistratal Markov model is constructed. Finally， the mid/long term photovoltaic simulating output is generated by utilizing the bistratal sampling. Compared with the K-means clustering analysis， spectral clustering is more suitable for processing photovoltaic output data， especially in the condition of data missing or data error and in distinguishing weather data. Through the comparative analysis on statistical characters， timing characters and weather characters， the validity of the proposed model is verified.

Key words: Markov model, spectral clustering, mid/long term photovoltaic output simulation

CLC Number:

TM 615

XU Shanshan， ZHU Junpeng， YUAN Yue， WU Han. Clustering and Simulation of Photovoltaic Output Adopting Markov Model[J]. Electric Power Construction, 2019, 40(2): 54-62.

References

［1］金黎明，周宁，冯丽，等. 光伏发电系统的时序概率模型研究［J］. 电力建设， 2016， 37（7）: 27-32.
JIN Liming， ZHOU Ning， FENG Li， et al. Chronological probability model of photovoltaic generation system［J］. Electric Power Construction， 2016， 37（7）: 27-32.
［2］张曦，康重庆，张宁，等. 太阳能光伏发电的中长期随机特性分析［J］. 电力系统自动化， 2014， 38（6）: 6-13.
ZHANG Xi， KANG Chongqing， ZHANG Ning， et al. Analysis of mid/long term random characteristics of photovoltaic power generation［J］. Automation of Electric Power Systems， 2014， 38（6）: 6-13.
［3］GRAHAM V A， KGT H. A method to generate synthetic hourly solar radiation globally［J］. Solar Energy， 1990， 44（6）: 333-341．
［4］姜晓亮，李巍，吕项羽，等. 基于非参数核密度估计法的光储系统容量优化配置［J］. 高电压技术， 2015， 41（7）: 2225-2230.
JIANG Xiaoliang， LI Wei， L Xiangyu， et al. Optimization configuration of photovoltaic-storage system capacity based on non-parametric kernel density estimation［J］. High Voltage Engineering， 2015， 41（7）: 2225-2230.
［5］管霖，陈旭，吕耀棠，等. 适用于电网规划的光伏发电概率模型及其应用［J］. 电力自动化设备， 2017， 37（11）: 1-7.
GUAN Lin， CHEN Xu， L Yaotang， et al. Probability model of PV generation for power system planning and its application［J］. Electric Power Automation Equipment， 2017， 37（11）: 1-7.
［6］朱想，居蓉蓉，程序，等. 组合数值天气预报与地基云图的光伏超短期功率预测模型［J］. 电力系统自动化， 2015， 39（6）: 4-10．
ZHU Xiang， JU Rongrong， CHENG Xu， et al. A very short-term prediction model for photovoltaic power based on numerical weather prediction and ground-based cloud images［J］. Automation of Electric Power Systems， 2015， 39（6）: 4-10．
［7］王育飞，付玉超，孙路，等. 基于混沌-RBF神经网络的光伏发电功率超短期预测模型［J］. 电网技术， 2018， 42（4）: 1110-1116．
WANG Yufei， FU Yuchao， SUN Lu， et al. Ultra-short term prediction model of photovoltaic output power based on chaos-RBF neural network［J］. Power System Technology， 2018， 42（4）: 1110-1116．
［8］单英浩，付青，耿炫，等. 基于改进BP-SVM-ELM与粒子化SOM-LSF的微电网光伏发电组合预测方法［J］. 中国电机工程学报， 2016， 36（12）: 3334-3342.
SHAN Yinghao， FU Qing， GENG Xuan， et al. Combined forecasting of photovoltaic power generation in microgrid based on the improved BP-SVM-ELM and SOM-LSF with particlization［J］. Proceedings of CSEE， 2016， 36（12）: 3334-3342.
［9］史佳琪，张建华. 基于深度学习的超短期光伏精细化预测模型研究［J］. 电力建设， 2017， 38（6）: 28-35.
SHI Jiaqi， ZHANG Jianhua. Ultra short-term photovoltaic refined forecasting model based on deep learning［J］. Electric Power Construction， 2017， 38（6）: 28-35.
［10］陈中，宗鹏鹏. 基于样本扩张灰色关联分析的光伏出力预测［J］. 太阳能学报， 2017， 38（11）: 2909-2915．
CHEN Zhong， ZONG Pengpeng. PV output forecast based on grey correlation analysis with expanded sample［J］. Acta Energine Solaris Sinica， 2017， 38（11）: 2909-2915．
［11］JI W， CHEE K C. Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN［J］. Solar Energy， 2011， 85（5）: 808-817．
［12］KARNER O. ARIMA representation for daily solar irradiance and surface air temperature time series［J］. Journal of Atmospheric and Solar-Terrestrial Physics， 2009， 71（8-9）: 841-847．
［13］罗钢，石东源，陈金富，等. 风光发电功率时间序列模拟的MCMC方法［J］. 电网技术， 2014， 38（2）: 321-327．
LUO Gang， SHI Dongyuan， CHEN Jinfu， et al. A Markov chain Monte Carlo method for simulation of wind and solar power time series［J］. Power System Technology， 2014， 38（2）: 321-327．
［14］丁明，鲍玉莹，毕锐. 应用改进马尔科夫链的光伏出力时间序列模拟［J］. 电网技术， 2016， 40（2）: 459-464．
DING Ming， BAO Yuying， BI Rui. Simulation of PV output time series used improved Markov chain［J］. Power System Technology， 2016， 40（2）: 459-464．
［15］江雪辰，朱俊澎，袁越，等. 基于新型场景划分与考虑时序相关性的光伏出力时间序列模拟方法［J］. 电力建设， 2018， 39（10）: 63-70.
JIANG Xuechen， ZHU Jupeng， YUAN Yue， et al. Simulation method based on improved scenario division considering temporal correlation for PV output time series［J］. Electric Power Construction， 2018， 39（10）: 63-70.
［16］盛万兴，季宇，吴鸣，等. 基于改进模糊C均值聚类算法的区域集中式光伏发电系统动态分群建模［J］. 电网技术， 2017， 41（10）: 3284-3291．
SHENG Wanxing， JI Yu， WU Ming， et al. Dynamic clustering modeling of regional centralized photovoltaic power plant based on improved fuzzy C-means clustering algorithm［J］. Power System Technology， 2017， 41（10）: 3284-3291．
［17］叶林，陈政，赵永宁，等. 基于遗传算法-模糊径向基神经网络的光伏发电功率预测模型［J］. 电力系统自动化， 2015， 39（16）: 16-22．
YE Lin， CHEN Zheng， ZHAO Yongning， et al. Photovoltaic power forecasting model based on genetic algorithm and fuzzy radial basis function neural network［J］. Automation of Electric Power Systems， 2015， 39（16）: 16-22．
［18］POGGI P， NOTTON G， MUUSELLI M， et al. Stochastic study of hourly total solar radiation in Corsica using a Markov model［J］. International Journal of Climatology， 2015， 20（14）: 1843-1860.
［19］姚世通. 基于隐马尔可夫模型的时间序列聚类的研究［D］. 上海: 上海交通大学， 2011.
YAO Shitong. A survey of hidden Markov model based clustering algorithm on time series［D］. Shanghai: Shanghai Jiao Tong University， 2011.

[1]	SUN Yi， LI Haoyang， LIU Yaoxian， QI Bing， LI Bin， ZHANG Xudong， LI Fei. Non-Intrusive Home-Load Identification Based on Improved Hidden Markov Model [J]. Electric Power Construction, 2020, 41(4): 73-80.
[2]	LIU Yang，YAN Zheng，MA Hongyan，XU Xiaoyuan. Reserve Dynamic Zone Partitioning Method Based on Semi-Supervised Clustering Considering Wind Power [J]. Electric Power Construction, 2018, 39(1): 90-.