Scholarlink

Nowadays, renewable energy sources play an important role in the process of generating electricity. Their use significantly reduces \(\mathrm{{CO}}_2 \) emissions which negatively affect the environment of our planet. One of the most popular methods of producing so-called green energy is the use of photovoltaic (PV) solar panels. Many factors affect on efficiency of the PV system, e.g. sun ray angle of incidence, type of panels, type of inverter, etc. However, these factors can be easily adjusted by the user. On the other hand, there are factors dependent on weather conditions, e.g. temperature, cloud cover, and humidity. In this paper, we propose an approach that uses selected artificial intelligence methods to choose the most characteristic weather-based features that affect on production of electric power value. It will allow one to effectively predict PV system production value for different locations and select one of them to build a solar power plant.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PV Solar Power Forecasting Using a Subset of Characteristic Features Selected by AI Methods

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tomasz Szczepanik,
  • Marcin Zalasiński

摘要

Nowadays, renewable energy sources play an important role in the process of generating electricity. Their use significantly reduces \(\mathrm{{CO}}_2 \) emissions which negatively affect the environment of our planet. One of the most popular methods of producing so-called green energy is the use of photovoltaic (PV) solar panels. Many factors affect on efficiency of the PV system, e.g. sun ray angle of incidence, type of panels, type of inverter, etc. However, these factors can be easily adjusted by the user. On the other hand, there are factors dependent on weather conditions, e.g. temperature, cloud cover, and humidity. In this paper, we propose an approach that uses selected artificial intelligence methods to choose the most characteristic weather-based features that affect on production of electric power value. It will allow one to effectively predict PV system production value for different locations and select one of them to build a solar power plant.