Abstract
Performing future load studies has become increasingly important on electric power distribution systems heavily penetrated with distribution generation. Forecasting the peak demand on distribution feeders a day or more in advance is one of many critical pieces of data needed to perform such studies. Weather forecasting has a significant impact on the peak daily load on distribution feeders where residential and commercial customers make up most of the load. Because distribution load on each feeder is driven by significantly fewer customers, it is more variable and difficult to model than that seen by traditional transmission and generation systems. The study in this paper presents how neural networks can use historical weather and SCADA load data to learn the unique characteristics of each feeder. The results with the neural network approach prove the potential to accurately forecast the peak load current on utility feeders based on the daily weather forecast.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
