Day-ahead Prediction of Photovoltaic Power Generation Based on Multi-type Weather Identification

YANG Xiu; YAN Zhongyu; SUN Gaiping; XIONG Xuejun; FENG Yuyao

doi:10.19725/j.cnki.1007-2322.2024.0007

您当前的位置：

首页 >

文章列表页 >

Day-ahead Prediction of Photovoltaic Power Generation Based on Multi-type Weather Identification

更新时间：2026-04-02

- Day-ahead Prediction of Photovoltaic Power Generation Based on Multi-type Weather Identification
- Vol. 43, Issue 2, Pages: 253-264(2026)
- 作者机构：
  
  1. 上海电力大学电气工程学院, 上海市杨浦区,200090
  2. 国网上海市电力公司电科院, 上海市虹口区,200092
- 作者简介：
- 基金信息：
- DOI：10.19725/j.cnki.1007-2322.2024.0007
  CLC： 2
- Published：2026
- 稿件说明：
移动端阅览
YANG Xiu, YAN Zhongyu, SUN Gaiping, et al. Day-ahead Prediction of Photovoltaic Power Generation Based on Multi-type Weather Identification[J]. 2026, 43(2): 253-264.
DOI：

YANG Xiu, YAN Zhongyu, SUN Gaiping, et al. Day-ahead Prediction of Photovoltaic Power Generation Based on Multi-type Weather Identification[J]. 2026, 43(2): 253-264. DOI： 10.19725/j.cnki.1007-2322.2024.0007.

摘要

针对光伏出力在转折性天气下短时间内功率发生剧烈波动导致预测精度降低的问题，提出一种基于多类型天气识别的光伏功率日前预测方法。对于天气识别，提出一种多层划分的新型模型。首先，采用天气状态指数反映气象特征；其次，利用高斯混合模型，聚类提取功率波动特征；最后，基于概念漂移算法将二者交叉，区分出转折天气日与4种平稳天气日，提升天气类型识别的精细度。对于功率预测，提出一种基于分位数回归的区间预测模型。首先，根据传递熵分别选择5种天气类型显著的气象特征，充分考虑天气模式的特异性；其次，提高模型的泛化能力，将多层感知器神经网络、卷积神经网络、双向长短期记忆神经网络模块化集成；然后，结合神经网络分位数回归模型生成预测区间；最后，采用中国上海地区一光伏电场数据，以验证所提模型在点预测、区间预测上的有效性。

Abstract

In response to the issue of the drastic fluctuation in PV power output in a short period of time under transitional weather

which will result in lower prediction accuracy

a PV power day-ahead prediction method is proposed based on multi-type weather identification. A new model with multi-layer division is proposed for weather identification. Firstly

the weather state index is utilized to reflect the weather characteristics. Secondly

a Gaussian mixture model is employed to extract the power fluctuation characteristics in clustering way. Finally

these two models are crossed and combined based on the concept drift algorithm

so as to distinguish the turning weather days and four kinds of smooth weather days for improving the weather type identification precision. Meanwhile

an interval prediction model based on quantile regression is proposed for power prediction. Firstly

the significant meteorological features of the five weather types are selected according to the transfer entropy respectively

taking into full consideration the specificity of weather patterns. Subsequently

to enhance the model’s generalization ability

the multilayer perceptron neural network

convolutional neural network

and bidirectional long- and short-term memory neural network are modularly integrated. Finally

the neural network quantile regression model is combined and the prediction interval is generated. The effectiveness of the proposed model in point prediction and interval prediction is verified using the data collected from a photovoltaic field located in Shanghai

China.

关键词

Keywords

references

DONG Cun, WANG Zheng, BAI Jieyu, et al . Review of ultra-short-term forecasting methods for photovoltaic power generation[J ] . High Voltage Engineering, 2023, 49(7): 2938−2951(in Chinese).

State Grid Corporation of China Releases Action Plan for "Carbon Peak and Carbon Neutrality"[N]. State Grid News, 2021-03-02(001).

AMEUR A, BERRADA A, LOUDIYI K, et al . Forecast modeling and performance assessment of solar PV systems[J ] . Journal of Cleaner Production, 2020, 267(3): 122167.

ABDEL-NASSER M, MAHMOUD K. Accurate photovoltaic power forecasting models using deep LSTM-RNN[J]. Neural Computing Applications, 2019, 31(7): 2727−2740.

YU D, CHOI W, KIM M, et al . Forecasting day-ahead hourly photovoltaic power generation using convolutional self-attention based long short-term memory[J ] . Energies, 2020, 13(15): 4017−4025.

YANG Jingxian, ZHANG Shuai, LIU Jichun, et al . Short-term photovoltaic power prediction based on variational mode decomposition and long short-term memory with dual-stage attention mechanism[J ] . Automation of Electric Power Systems, 2021, 45(3): 174−182(in Chinese).

MUNKHAMMAR J, VAN DER MEER D, WIDÉN J. Probabilistic forecasting of high-resolution clear-sky index time-series using a Markov-chain mixture distribution model[J]. Solar Energy, 2019(184): 688−695.

WANG Fei, MI Zengqiang, ZHEN Zhao, et al . A classified forecasting approach of power generation for photovoltaic plants based on weather condition pattern recognition[J ] . Proceedings of the CSEE, 2013, 33(34): 75−82(in Chinese) .

LI F, LIN Y L, GUO J P, et al . Novel models to estimate hourly diffuse radiation fraction for global radiation based on weather type classification[J ] . Renewable Energy, 2020(157): 1222−1232.

YAN Yixun, WANG Lijie, GUO Hongwu, et al . Short-term photovoltaic power prediction based on multi-feature analysis and extraction[J ] . High Voltage Engineering, 2022, 48(9): 3734−3743(in Chinese).

YE Lin, PEI Ming, LU Peng, et al . Combination forecasting method of short-term photovoltaic power based on weather classification[J ] . Automation of Electric Power Systems, 2021, 45(1): 44−54(in Chinese).

SHENG Hanmin, XIAO Jian, CHENG Yuhua, et al . Short-term solar power forecasting based on weighted gaussian process regression[J ] . IEEE Transactions on Industrial Electronics, 2018, 65(1): 300−308.

CHEN Zhibao, DING Jie, ZHOU Hai, et al . A model of very short-term photovoltaic power forecasting based on ground-based cloud images and RBF neural network[J ] . Proceedings of the CSEE, 2015, 35(3): 561−567(in Chinese).

WANG Fei, ZHEN Zhao, MI Zengqiang, et al . Solar irradiance feature extraction and support vector machines based weather status pattern recognition model for short-term photovoltaic power forecasting[J ] . Energy and Buildings, 2015(86): 427−438.

LI Jinghua, LUO Yichen, YANG Shuhui, et al . HUANG Qian. A review of uncertainty prediction methods for renewable energy power[J ] . High Voltage Technology, 2021, 47(4): 1144−1157(in Chinese).

GOLESTANEH F, PINSON P, GOOI H B. Very short-term non-parametric probabilistic forecasting of renewable energy generation-with application to solar energy[J]. IEEE Trans-actions on Power Systems, 2016, 31(5): 3850−3863.

HE Yaoyao, QIN Yang, WANG Shuo, et al . Electricity consumption probability density forecasting method based on LASSO-quantile regression neural network[J ] . Applied Energy, 2019(233-234): 565−575.

ZHAO Kangning, PU Tianjiao, WANG Xinying, et al . Probabilistic forecasting for photovoltaic power based on improved Bayesian neural network[J ] . Power System Technology, 2019, 43(12): 4377−4386(in Chinese).

HU Tianyu, GUO Qinglai, LI Zhengshuo, et al . Distribution-free probability density forecast through deep neural networks[J ] . IEEE Transactions on Neural Netw orks and Learning Systems, 2020, 31(2): 612−625.

XU Biao, XU Qingshan, HUANG Yu, et al . Day-ahead probabilistic forecasting of photovoltaic power based on vine copula quantile regression[J ] . Power System Technology, 2021, 45(11): 4426−4434 (in Chinese).

MU Dongliang, HAN Meng, LI Ang, et al . Overview of classification methods for complex data streams with concept drift[J ] . Journal of Computer Applications, 2023, 43(6): 1664−1675(in Chinese).

GAMA J, MEDAS P. Learning with drift detection[J]. Advances in Artificial Intelligence-SBIA, 2004(3171): 286−295.

GIGONI L, BETTI A, CRISOSTOMI E, et al . Day-ahead hourly forecasting of power generation from photovoltaic plants[J ] . IEEE Transactions on Sustainable Energy, 2017, 9(2): 831−842.

SCHREIBER T. Measuring information transfer[J]. Physical Review Letters, 2000, 85(2): 461−464.

MA J, SUN Z Q. Mutual information is copula entropy[J]. Tsinghua Science and Technology, 2011, 16(1): 51−54.

TAYLOR J W. A quantile regression neural network approach to estimating the conditional density of multiperiod returns[J]. Journal of Forecasting, 2000, 19(4): 299−311.

Views

101

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Ultra Short Term Load Power Prediction Considering Feature Recombination and BiGRU-Attention-XGBoost Model

A Lightweight Outage Perception Model for Power Grids Based on Prompt Learning From Multi-source Outage Data

A Power Quality Disturbance Analysis Method Based on Blockchain and Secure Computation

A Method to Detect False Data Injection Based on Feature Mapping and Deep Learning

New Design of Self-Explosive Insulator Detection Model Based on Generative Adversarial Network

Related Author

Shasha ZHAO

Chao ZHANG

Wenjie FU

Weiguang CHEN

Guoqiang GAO

Lianbing LI

Xiaodong GUO

Shaolei WU

Related Institution

State Grid Hebei Electric Power Co., Ltd. Marketing Service Center

State Grid Hebei Electric Power Co., Ltd.

School of Artificial Intelligence and Data Science, Hebei University of Technology, Hongqiao District

State Key Laboratory of Electrical Equipment Reliability and Intelligence(Hebei University of Technology), Hongqiao District

Anhui Electric Power Corporation

AI问答

⁰