A Prediction Method of Solar Power Generator using Machine Learning Techniques

  • Jungseok Cho
  • Jeongdoo Lee
  • Doosan ChoEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 931)


We first purchased a solar power generator, installed it in the right place, and then collected power generation data for the next 12 months. First, we collected weather and power generation data to excel file. For the weather data, the data provided by meteorological agency was secured to ensure the reliability of the information. The collected data can be monitored anytime and anywhere using PC or mobile device. The user interface of these services is planned to be upgraded to be more usable after the accuracy of the service provided. The core development contents are collected data based power generation prediction technique. This is because system failure monitoring can be performed only when a power generation prediction system is configured. Our power generation prediction algorithm was developed based on machine learning. LSTM was used among linear regression and artificial neural network in machine learning. Experiments using the machine learning showed that the accuracy could be increased to 85% when compared with actual power generation.



This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2018R1D1A1B07050054), and project (Grants No. C0396335) for Cooperative R&D between Industry, Academy, and Research Institute funded Korea Ministry of SMEs and Startups in 2016.


  1. 1.
    Choi, S.-H., Oh, D.-E.: The technical trend and prospect of platform integration for smart grid system. In: The Korean Institute of Electrical Engineers for the 42nd Summer Conference, pp. 1977–1978 (2011)Google Scholar
  2. 2.
    Kao, C., Chyu, C.-L.: Least-squares estimate in fuzzy regression analysis. Eur. J. Oper. Res. 148(2), 426–435 (2003)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Koutroulis, E., Kalaitzakis, K.: Development of an integrated data acquisition system for renewable energy sources systems monitoring. Renew. Energy 28(1), 139–152 (2003)CrossRefGoogle Scholar
  4. 4.
    Forero, N., Hernandez, J., Gordillo, G.: Development of a monitoring system for a PV solar plant. Energy Conv. Manag. 47(15–16), 2329–2336 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Sunchon National UniversitySuncheonKorea

Personalised recommendations