Kyungpook National University Industry-academic Cooperation Foundation

Dongjun Suh

Minjeong Sim

Junhwa Hwang

Geonkyo Hong

Bowoo Kim

Disclosed is a solar energy management method using deep reinforcement learning including receiving, by at least one processor, at least one or more pieces of energy information data for deep reinforcement learning of a deep neural network, calculating, by the at least one processor, a reward value for controlling a solar energy management algorithm constituting the deep neural network using the at least one or more pieces of energy information data and performing the deep reinforcement learning, and determining, by the at least one processor, a schedule for storing, discharging, consuming or selling solar energy by inputting the at least one or more pieces of energy information data as input data of the solar energy management algorithm.

Solar energy management method and system using deep reinforcement learning

A prediction system for solar photovoltaic generation includes a region setter that sets a target region where a solar panel is installed and an adjacent region adjacent to the target region, a first data collector that collects numerical weather data of the target region and adjacent region and an amount of the solar photovoltaic generation obtained from the solar panel, a second data collector that collects weather image data of the target region and adjacent region by using a satellite image, a controller that determines whether the target region is affected by wind by comparing the weather image data to each other, and a deep learner that predicts the weather image data of the target region, and predicts the amount of the solar photovoltaic generation by using the amount of the solar photovoltaic generation, the numerical weather data and weather image data of the target region.

Growing community of inventors

Gimcheon-si, South Korea

Dongjun Suh