首页>
外国专利>
APPRATUS AND METHOD FOR ESTIMATION OF WEEKLY POWER LOAD TO IMPROVE PROCESSING TIME USING NEURAL NETWORK AND REVISION FACTOR
APPRATUS AND METHOD FOR ESTIMATION OF WEEKLY POWER LOAD TO IMPROVE PROCESSING TIME USING NEURAL NETWORK AND REVISION FACTOR
展开▼
机译:利用神经网络和修订因子估算每周电力负荷以改善处理时间的装置和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to an apparatus and method for predicting a weekly load using a neural network and an average load curve, and more particularly, to a data collection unit for continuously collecting a unit time electric power consumption, A neural network training unit for training a neural network so as to generate a predicted daily power consumption value, and a predicted value of a temporary power consumption amount for the next week using the neural network training unit and the collected unit time power consumption, And a predicted value generation unit for generating a correction coefficient by using the daily power use amount between the predicted last week and generating the predicted power consumption value for the next week by applying the correction coefficient only when the correction coefficient is included in the preset correction coefficient range Including the weekly load forecasting device To the invention of being able to improve the service response time of the application services, such as instant planning, or power demand reduction using real-time load balancing for power users.
展开▼