- Customer Success Stories
- Northern Virginia Electric Cooperative (NOVEC)
Electric co-op relies on analytics to forecast demand, transmission needs
SAS helps NOVEC provide stable, competitively priced power for its consumers.
21.7% improvement
in forecasting over the competing model
Company achieved this using • SAS® Analytics Pro • SAS® Enterprise Guide® • SAS/ETS®
The Northern Virginia Electric Cooperative (NOVEC) provides power to 169,000 customers. To keep electric costs down and to reliably serve customers, NOVEC needs to know how much power to buy, transmit and deliver for its consumers. SAS® Analytics provide NOVEC with a broad array of econometric and time series forecasting techniques, along with point-and-click interfaces that can grow with the utility.
SAS has the functionality to do what we need now and what we anticipate needing in the future. Jamie Hall Senior Operations Research Analyst NOVEC
Challenges for NOVEC
NOVEC doesn't produce its own power. The co-op needs to forecast power consumption accurately to make power purchasing decisions that will result in stable, competitively priced power for its consumers.
It must prudently provision for new or upgraded facilities such as substations and lines as its consumer base and consumer load grow.
NOVEC must optimally operate and maintain its electric infrastructure in order to provide superior service reliability at a competitive cost to its consumers.
Why SAS?
"Stability. SAS has the functionality to do what we need now and what we anticipate needing in the future. It's the safe choice,'' says Jamie Hall, Senior Operations Research Analyst.
"Ease of use. NOVEC analysts can point and click to build a model, making the product accessible to anyone," says Ananya Kassahun, NOVEC Business Analyst. She had not used SAS before joining NOVEC.
NOVEC – Facts & Figures
169,000
residents and businesses receive electricity via NOVEC
7,200+
miles of electric lines
99.99%
average system reliability
SAS benefits
SAS automatically keeps track of the flow of the forecasting process and upwards of 50 time series used to build models.
Pulling in third-party and historical data from multiple sources is simple. The models use daily third-party weather forecasts and monthly economic information.
The model built in SAS provided a 21.7 percent improvement versus the competing model.
Future SAS uses
Determining the impact of load management programs.