Finding your crystal ball
- April 23, 2015
- 263 views
Analytics is an integral part of this business, but, whether it is due to lack of data or expertise, the business case to invest in analytics has been hard to nail down. But what if your company had a crystal ball for analytics? How easy would it be to make the case then?
The traditional folk tale’s crystal ball foretold the future: what will happen, what won’t, love coming in, love going out. A business-specific one, though not as lovey-dovey, could give you 100 percent accurate answers to questions such as:
- What's the revenue for the next five years? From what lines of business?
- When is the next price spike in the electricity market? How much will it be?
- What's the peak demand tomorrow?
- How many transformers will be taken down by the storm next week?
- How many customers will buy electric vehicles next year?
So, forget that traditional crystal ball. Instead, how much would you pay for this business-accurate one?
The valuation for this perfect crystal ball should depend upon many factors, such as:
- How big the business is. The bigger the company is, the more potential value this crystal ball has.
- How good (or bad) the existing practice is. If you have already known the future with 100 percent accuracy, then the crystal ball worth nothing. If you currently have a very poor forecast of the future, then the crystal ball may be quite valuable.
- How this crystal ball is being used. Are you using it across your entire enterprise, or are you using it in one of the departments, such as power supply, customer services, or transmission planning? As this crystal ball moves up the organization chart, its value apparently grows significantly. The efforts needed to estimate the value also grows accordingly.
This list can go on and on. After evaluating all possible driving factors of the valuation, I'm sure you will end up with too complex a problem to get a defendable answer. Instead of pursuing the perfect valuation with endless analysis and debates, we can try to get in the ballpark with reasonable efforts, considering just one business area of forecasting (and a little “crystal-ball thinking” in the form of predictive analytics).
Load forecasting: Three magic numbers for your back-of-the-envelope calculations
Let’s first consider a utility with 1GW annual peak. Assuming this utility uses long-term load forecast for generation planning only, how much shall we value the crystal ball if it can improve the company’s forecast accuracy by 1 percent?
- The risk of over or under sizing power plant is:1000MW X 1% = 10MW
- Assuming the capital cost is $10000/kW, the overnight capital cost is: $1000/kW X 10MW = $10M
- Savings of deferring $10M spending for one year (5% interest rate): $10M – $10M / (1 + 0.05) = $476K (~$500K)
Therefore, the crystal ball can be valuated at $500K/year for improving the forecasting accuracy of a 1GW peak utility by 1 percent.
Assuming this utility uses short-term load forecast for securing energy in the day-ahead market only, how much shall we value the crystal ball if it can improve the company’s forecast accuracy by 1 percent? What if the crystal ball can also predict the prices in day-ahead and real-time markets?
Predicting the weather
Electricity demand is heavily driven by weather, and most market participants use similar sources of weather forecasts. When you, as a typical market participant, are under-forecasting (or over-forecasting) the day-ahead demand, most others are experiencing the same. As a result, if you have bought more than actual in the day-ahead market, you have to sell the energy in the real-time market at a lower price. If you have not bought enough in the day-ahead market, you have to buy energy in the real-time market at a higher price. In other words, you almost always lose money in the real-time market due to the day-ahead forecast errors.
Let’s take ISO New England’s demand and price data for the last decade (2005 – 2014). We first standardize the hourly demand so that the standardized peak load of each year is 1GW. Now ISO New England is in the same size as that 1GW peak utility. We can calculate the cost of 1 percent demand being placed in the high-price market.
Without a price forecast, we would try to place as much demand in the day-ahead market as possible, because the day-ahead market is less volatile than the real-time market. We can calculate the cost of placing 1 percent of the demand in day-ahead market. With a price forecast, we know which market has a lower price, so that we can place that 1 percent demand in the low-price market. We can calculate the associated cost as well. Comparing with placing the 1 percent demand in the high-price market, we can then obtain the savings for both cases as listed in the table.
On average, the predictive analytics crystal ball saves about $300K/year for improving the company’s short-term load forecast accuracy by 1 percent. With the additional price forecasts, the savings can go up to $600K/year.
Based on the aforementioned calculations, here are three magic numbers for your back-of-the-envelope calculations, all based on 1 percent improvement on a 1GW peak utility:
- Long-term load forecasting: $500K/year
- Short-term load forecasting: $300K/year
- Short-term load and price forecasting: $600K/year
For a typical medium-size utility with 5GW peak, taking an integrated load forecasting approach to improve long-term load forecasts by 3 percent and short-term load forecasts by 1 percent, the total annual savings would be around: ($500K X 3 + $300K X 1) X 5 = $9M.
As a ballpark estimate, this means that the actual annual savings will most likely fall between $4.5M and $18M, but not outside the range between $0.9M and $90M.
Finding your crystal ball
These “crystal ball” numbers aren’t reality, of course. In reality, due to the stochastic nature of the world, such a crystal ball does not exist. Nevertheless, you always have access to predictive analytics, which helps forecast the future. Even if your analysis returns half of the value estimated from the “crystal ball” we talked about here, it is a strong return on investment, particularly when multiplied across other areas of the business.
The usefulness of your forecast to drive improved organizational efficiency and improved decision-making is mostly under your control. Forecasts can always be improved, and they are as close to a “crystal ball” that you can own right now. The question is: How much are you willing to invest in them to make your vision of the future the most accurate you can get?
Dr. Tao Hong is EPIC assistant professor, graduate program director of engineering management and NCEMC faculty fellow of energy analytics at the University of North Carolina at Charlotte. He can be reached at drhongtao.com.
This piece is a feature article for our sister magazine Energy Biz’s new print issue. You can read this article again (and all the other good info contained in those pages) by downloading a PDF of that print issue absolutely free. Just click here.