About this paper
Utility forecasters cannot assume that one methodology will provide the best forecast from one year to the next. To improve forecast performance, reduce uncertainties and generate value in the new data-intensive environment, they must be able to decide which models, or combinations of models, are best. And they must be able to determine more indicators of the factors that affect load. This paper uses a case study to illustrate how utility forecasters can take advantage of hourly or sub-hourly data from millions of smart meters by using new types of forecasting methodologies. It investigates how a number of approaches using geographic hierarchy and weather station data can improve the predictive analytics used to determine future electric usage. It also demonstrates why utilities need to use geographic hierarchies, and why their solutions should allow them to retrain models multiple times each year.
SAS는 분석 부문의 선두 기업입니다. SAS의 혁신적인 소프트웨어와 서비스는 전세계 고객사가 데이터를 기반으로 인텔리전스를 극대화할 수 있도록 지원합니다. SAS는 THE POWER TO KNOW®를 실현합니다.