ELECTRONIC DEVICE FOR PREDICTING LONG-TERM PHOTOVOLTAIC POWER GENERATION USING METEOROLOGICAL AND SEASONAL INFORMATION BASED ON DEEP LEARNING AND OPERATING METHOD THEREOF

摘要

The present invention relates to an electronic device for predicting a long-term photovoltaic power generation amount based on a deep learning using meteorological and seasonal information, and an operating method thereof. According to various embodiments disclosed herein, the electronic device for predicting a long-term photovoltaic power generation amount based on a deep learning using meteorological and seasonal information includes: a storage unit for storing meteorological information and seasonal information received from the outside; a model management unit for determining values of one or more variables to be set in at least one model used to calculate an expected amount of photovoltaic power generation by using the meteorological information and the seasonal information in response to the number of each of the meteorological information and the seasonal information which is equal to or more than a preset threshold; a model learning unit for progressing a learning for the at least one model until a predetermined number of times by using the meteorological information and the seasonal information, after the determined one or more variables are set to the at least one model; and a power generation calculation unit for calculating an expected amount of the photovoltaic power generation by using the at least one model having been trained for the predetermined number of times.