How the Southwest Was Really Won
Salt River Project Tames Wholesale Energy Market with Help from SAS®
Arizona is a land of extremes: In the northern part of the state, temperatures dip to nearly zero degrees Fahrenheit amid snowfall in winter while the southern desert bakes in 110-degree heat in the summer. Yet the Grand Canyon state remains one of the most desirable places to live in the United States.
That's, in part, thanks to the work going on at Salt River Project (SRP). SRP, based in Phoenix, was established in 1903 as the nation's first multipurpose reclamation project authorized under the National Reclamation Act. Today, SRP is the nation's second-largest public power utility (based on net generation in megawatt-hours) and one of Arizona's largest water suppliers, providing power to about 960,000 retail customers throughout a 2,900-square-mile service territory in central Arizona.
SRP operates or participates in thirteen major power plants as well as hydroelectric facilities throughout the Southwest.
We're talking tens of millions of dollars in what this group does, so the impact of SAS has to be in the millions.
Principle Planning Analyst
Lowering Customer Costs
SRP's primary responsibility is to deliver low-cost water and electricity to its customers. Having domesticated the desert, SRP now brings the sometimes wilder extremes of the wholesale electricity market under control with help from SAS. Electricity costs are ultimately determined in a real-time market where suppliers and generators buy and sell power based on current load availability and consumer demand. With SAS, SRP accurately forecasts for up to 36 months how much excess power it will have available for wholesale sales.
"To be successful in the wholesale electric industry, you must have very good models. Models help project where you have excess electricity, and subsequently, you can make better decisions on when and how much you can sell," explains Mike Krause, marketing representative in SRP's supply and trading group.
For example, traders need to know how an outage at a power plant will affect value on certain deals or whether excess power will even be available to sell. Or what will happen to net revenues if retail load takes an unexpected dip. "We can flip a switch in our model and minutes later have that output in our hands," says Harry Sauthoff, Principal Planning Analyst .
Harnessing the Data
To create the model, the supply and trading team first had to harness all the operational data for all 24 hours, seven days a week. Again, they turned to SAS - this time to build a data mart to unify under one roof all the data relating to customer demand, supply, generation, trades and sales scattered in pockets and pools throughout the company. "The data mart evolved out of the need to access and assemble the data to project how much excess electricity we have," Krause says.
"We knew SAS would allow us to grab the data from all the various sources, and there were a lot of sources of information we needed to feed the model set. We picked SAS because we had staff with SAS skills and knew it could get the job done – and get it done quickly."
Controlling Their Own Destiny
SRP's supply and trading team updates the model with market and trade information nightly, and they are no longer at the mercy of other departments for access to data. SAS gives them quick, easy access to 10 years' worth of information via Web browser. "Before we had SAS, we had to use programmers from our Information Technology group to give us downloads of the data we needed," says Steve Petruso, Senior Computer Analyst. "Now we can access the data ourselves, when we need it, with our own expertise."
SRP analysts now have direct access to the data in order to refine the model, test forecast techniques, and build a Web-reporting interface. To support trading, new forecast assumptions can be updated in just minutes – and the results are immediately available over the Web to all business users.
With such greatly improved reporting capability, the traders gain more insight into what they have available to sell – meaning they rarely have to debate their positions. That allows SRP to develop successful trading strategies and other groups can use the information for activities such as preparing budgets.
Confidence in the Numbers
The SAS data mart and Web-based reporting gives traders more confidence in the numbers because they always have access to the latest information. "That was a big problem with our old models," Sauthoff says. "Everytime we needed to make a decision, there was a lot of debate over whether the model was accurate. Now that we're using SAS, that debate is over." Also gone are the spreadsheets and manual entry required for modeling under the old paper-driven reporting system. And in addition to greatly improving its forecasting accuracy, SRP has discovered new ways of capitalizing on SAS software's Web-based reporting capabilities.
"Upon completion of the model and data mart, SRP traders now have confidence that they are capturing more opportunities than ever before," Sauthoff says. "We are constantly benchmarking our model with graphical and numeric analysis. This data is available daily and is used to refine our assumptions that drive our model. Moreover, anyone can access the forecast performance reports via the Web."
The trading group generates millions of dollars per year for SRP, and the supply and trading team gains valuable insights using SAS, allowing them to better manage load and how they sell excess energy. "We're talking tens of millions of dollars in what this group does, so the impact of SAS has to be in the millions," Sauthoff says. "And gains that we make are used to offset retail prices. So the revenues we generate go to help our customers."
Increase value by knowing when to sell excess electricity for the best price.
SAS helps pull together disparate data for translation into intelligence that feeds a sophisticated forecasting model that provides timely and accurate results.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.