APPARATUS CONTROL SYSTEM

To make a state in which surplus power to be used by an electrical apparatus is insufficient be hardly caused when weather of the current day differs from that forecast on the previous day.SOLUTION: An apparatus control system 100 is composed of power generation means 1, a controller 2, and an electric apparatus 3. The controller uses a learned model obtained by machine learning performed by taking past weather information and calendar information as input and power consumption as output to output predicted power consumption on the next day by taking forecast weather information on the next day and calendar information on the next day as input, calculates predicted surplus electric energy on the next day on the basis of the output predicted power consumption, determines whether to control the electric apparatus on the current day or the next day on the basis of the calculated predicted surplus electric energy, and controls the electric apparatus on the determined control day. The controller comprises a function for correcting, when it is determined that the next day is the control day, the predicted power consumption which was output on the previous day on the next day.SELECTED DRAWING: Figure 1 【課題】当日の気象が前日の予報と異なった場合に、電気機器で使用する余剰電力が不足する状態を起こりにくくする。【解決手段】機器制御システム１００は、発電手段１と、制御装置２と、電気機器３から成る。制御装置は、過去の気象情報及びカレンダー情報を入力とし消費電力量を出力として機械学習させた学習済モデルを用い翌日の予報気象情報及び翌日のカレンダー情報を入力として翌日の予測消費電力量を出力し、出力した予測消費電力量に基づいて翌日の予測余剰電力量を算出し、算出した予測余剰電力量に基づいて電気機器の制御日を当日にするか翌日にするかを判断し、判断した制御日に電気機器を制御する。また制御装置は、制御日を翌日にすると判断した場合、翌日になってから前日に出力した予測消費電力量を補正する機能を備える。【選択図】図１