SAS has introduced Energy Forecasting, which increases utility efficiency by capitalizing on new interval data from smart meters. SAS’ solution is different from other load forecasting software in that Energy Forecasting supports multiple planning horizons, from the next hour to the next half century.
Modern utilities need vigorous load forecasting to improve planning and operations while also ensuring that consumer retain power. The increasing volume and variety of data make analytics integral to prevent traditional forecasting systems and processes from being overwhelmed.
David Hamilton, manager of load forecasting for Old Dominion Electric Cooperative, says, “We saved utility customers millions of dollars in our first year using SAS. With SAS, we can capitalize on massive volumes of new data and quickly adjust to changing conditions. We needed to understand how our customers are likely to buy energy in the future. We couldn’t answer that question for the organization if we didn’t have SAS.”
The ability to predict the volume, variability, and location of energy demand can significantly improve a utility’s bottom line and ability to manage its resources.
SAS Global Marketing Manager for Energy and Utilities Alyssa Farrell notes, “Working with our customers, we developed SAS Energy Forecasting to go beyond what any forecaster has had access to before. We include utility-specific forecasting models and a comprehensive forecasting toolset for further refinement or custom configuration. Data mining and other analytical methods produce forecasts that more accurately reflect business realities and better guide decision makers ranging from load forecasters to senior executives.”
Andrew Mortimer, Forecasting Optimization Manager at RWE npower, adds: “We needed a forecasting solution that was more flexible and responsive to deal with variations in demand caused by a number of factors, including the general economic downturn, changes in market conditions and the unpredictable weather we’ve seen. Since adopting the SAS solution, we’ve seen a significant reduction in the error rate for commodity forecasting, driving considerable cost savings. We can now interrogate large data sets in a more efficient and effective way than previously, so I’d expect to see these cost savings sustained over the coming years.”© smartmeters.com. No Reproduction without permission.