|Autors: Andreev, O. D., BabamovaTsenova, V. B., Tsenov, G. T.|
Title: Application of Neural networks for time series electrical consumption forecasts
Keywords: —Neural Networks, Time series prediction, Electric Load Optimization
Abstract: With introduction of IoT there is possible to use nowadays cheap measurement devices that can store information form actuators and store it in databases locally or online. With the recent opening of the electrical distribution markets, it will be possible to buy electrical energy on varying prices and from various suppliers. With big time intervals of data collection for the plant consumption and of the market price fluctuations done with IoT devices for a relatively small time intervals on the recorded samples a user electrical power profile can be created by using neural networks as time series forecasts predictor. With such plant/user power profile the predicted production can be shifted towards the intervals with cheaper electricity prices leading to reduced production costs. This paper presents the results for creating an energy consumption profile with electrical loads forecasts, when they are presented as time series and by using the MATLAB’s Neural Networks Toolbox.
Full text of the publication
Вид: статия в списание, публикация в реферирано издание