×

ELECTRIC POWER SYSTEM

  • US 20100023174A1
  • Filed: 03/26/2007
  • Published: 01/28/2010
  • Est. Priority Date: 03/26/2007
  • Status: Active Grant
First Claim
Patent Images

1. An electric power system in which a plurality of electric power suppliers and demanders is mutually connected, the electric power supplier and demander being provided with one or a plurality of power generation devices, one or a plurality of electrical storage devices and one or a plurality of electric power consumption devices, and an electric power supply and demand control device,wherein each of said electric power supply and demand control devices judges whether or not electric power shortage is occurred or whether or not electric power surplus is occurred in each of said electric power suppliers and demanders provided with the electric power supply and demand control device, receives electric power from other electric power supplier and demander provided with said power generation device and/or said electrical storage device in the case where electric power shortage is occurred in the electric power supplier and demander, and controls to deliver electric power to other electric power supplier and demander in the case where electric power surplus is occurred in said electric power supplier and demander;

  • andcontrols the plurality of said power generation devices in respective electric power suppliers and demanders in the delivery and receipt of electric power among respective electric power suppliers and demanders,the control being automatically or manually performed based on that a pattern classification model for a neural network is formed in a computer,total production of electricity, maximum electric power demand, and total electric power demand of the following day are predicted based on at least past actual performance data, weather forecast and calendar information of the following day, and theoretical amount of solar radiation at fine weather of the day,actual performance data of the forecast items and weather, calendar information, and theoretical amount of solar radiation of a past fixed period including at least the day are collected for neural network relearning,the relearning is performed by an error back propagation algorithm based on the prediction data and actual performance data of the day, andthe total production of electricity, the amount of maximum electric power demanded, and the amount of total electric power demanded of the following day are predicted by an updated neural network.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×