A Prediction Method for Daily Photovoltaic Power Generation based on Datamining

HS Solar Energy Company Inc. in Sejong city, Korea, has a big problem on how to monitor heterogeneous inverters with different protocols. Still a current photovoltaic power plant with different inverters, it has attracted significant attention to its experience of difficulties in monitoring integrated power generation. To solve this problem for the company, we adapt a metamodel mechanism to easily manage and integrate heterogeneous data into a metamodel-based data format. The existing metamodel-based photovoltaic monitoring system (M-PVMS) of the HS solar energy company also needs to simply predict the photovoltaic power generation in a day for small farm owners in the countryside. Therefore, we propose a method for predicting the power generation of M-PVMS panels using the gated recurrent unit (GRU) algorithm, which supports real-time learning to predict the photovoltaic system behavior that rapidly accumulates data in real time. As a result, we can predict the power generation for small farm owners with a probability of 96.353%.

Download Full-text

Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information

The Journal of Korean Institute of Communications and Information Sciences ◽

10.7840/kics.2019.44.12.2231 ◽

2019 ◽

Vol 44 (12) ◽

pp. 2231-2238

Author(s):

Yongsu Kim ◽

Sanghyun Lee ◽

Howon Kim

Keyword(s):

Power Generation ◽

Prediction Method ◽

Weather Information ◽

Photovoltaic Power

Download Full-text

Research on Photovoltaic power prediction technology Based on Machine Learning

Journal of Physics Conference Series ◽

10.1088/1742-6596/2087/1/012004 ◽

2021 ◽

Vol 2087 (1) ◽

pp. 012004

Author(s):

Hongxia Li ◽

Jianlin Li ◽

Yang Mi

Keyword(s):

Machine Learning ◽

Power Generation ◽

Prediction Method ◽

Meteorological Factor ◽

Power Prediction ◽

Advantages And Disadvantages ◽

Photovoltaic Power ◽

Huge Impact ◽

Basic Technology ◽

Safety And Stability

Abstract In recent years, the photovoltaic power generation has obvious intermittent, randomness and volatility, and high permeability photovoltaic will have a huge impact on the safety and stability of the grid. The prediction of photovoltaic power generation is to improve the quality of photovoltaic grid, optimize grid scheduling, and ensure the basic technology of power grid safety and stability. In order to improve the prediction accuracy of photovoltaic power generation, this article will comprehensively carding and compare from 3 dimensions: photovoltaic power generation and meteorological factor correlation analysis, similar day selection, prediction method based on machine learning, and summarize the advantages and disadvantages of various methods. Further research has been put forward accordingly.

Download Full-text

Improved Artificial Bee Colony Algorithm Applied to Neural Network Photovoltaic Power Generation Prediction Method

E3S Web of Conferences ◽

10.1051/e3sconf/202018501012 ◽

2020 ◽

Vol 185 ◽

pp. 01012

Author(s):

Jiaxiong Zhu ◽

Jiang Qiang ◽

Chang Feng ◽

Cao Jing

Keyword(s):

Neural Network ◽

Power Generation ◽

Bp Neural Network ◽

Artificial Bee Colony Algorithm ◽

Artificial Bee Colony ◽

Prediction Method ◽

Weather Conditions ◽

Network Parameter ◽

Bee Colony ◽

Photovoltaic Power

With the increase in the use of renewable energy, especially the development and utilization of solar energy resources, accurate photovoltaic power generation prediction technology will help the promotion of photovoltaic power generation. The amount of photovoltaic power generation depends on weather conditions, and it is easy to produce large fluctuations under different weather conditions. Its power generation has the characteristics of randomness, fluctuation and intermittency. In view of the shortcomings of the traditional BP neural network prediction method, this paper proposes an improved artificial bee colony algorithm. The improved artificial bee colony algorithm is used to optimize the network parameter weights in the traditional BP algorithm, and the two algorithms are merged in global iteration. Based on the characteristics of training light intensity, weather, temperature and historical power value of photovoltaic output power,a photovoltaic power generation prediction model is established. The simulation results show that the improved artificial bee colony algorithm in the neural network’s photovoltaic power generation forecast improves the accuracy and convergence speed of the traditional BP neural network convergence solution, and can provide more comprehensive information for grid power dispatch and control.

Download Full-text