Our blogs Blogs home
Energy in Transition

Energy in Transition

General

Next-generation demand response forecasting – increasing the accuracy and speed of your forecasts

This author no longer works for DNV GL.

Does this sound familiar?

Your utility has demand response programs that shave peak when deployed, by between 40 and 80 MW total, depending on the day.  Some of this wide variation is due to weather differences, and then there’s the “random”—i.e., unexplained—error that makes up the rest.  For an upcoming event, your system planning group receives a MW performance forecast, but without a direct way to measure the program’s performance and the wide variability observed in post-event performance calculations compared with the forecasts, this program resource is seen as “fuzzy,” “soft,” or maybe even “cuddly”…ok maybe not cuddly, but certainly the other two.

What can be done to firm up the DR Resource?

Option 1: Beef up the measurement and communication systems

For direct load control programs, two-way communication switches have been available from vendors for a number of years.  These two-way switches can send information back to dispatchers and enable targeting of a specific number of committed MW for the program, through active monitoring or automated controls.  There are also non-intrusive load monitoring (NILM) systems which enable near real-time visibility into the power consumption by important appliances used within homes or businesses, which will provide the load shed through auto DR, direct load control, or other curtailment programs.  Communication back to the system operator can travel through AMI systems or dedicated cellular channels.  These technologies can be used to provide dramatic improvements in the accuracy of near real-time forecasts of load impacts.  But unfortunately they still do not include a crystal ball-like device for seeing what is going to happen tomorrow.

Option 2:  Micro-forecasting analytics

Whereas option 1 was focused on technology solutions, option 2 involves extracting more predictive power from smart meter and other data that is already being collected, and therefore has no additional data collection cost.  In a recent research demonstration with our utility partners, we were able to reduce day-ahead forecasting uncertainty for DR programs from a previous best-case accuracy of ±20% down to ±12% on average by using adaptive analytics.  The key to the adaptive analytics is to better understand and account for serial correlation, or, in other words, the degree to which data that is in close proximity in a time series is related.  So it’s not just developing relationships between data fields over a broad span of time, e.g., an event season, it’s about finding extra insights about what’s about to happen tomorrow, from cues in the data from yesterday and today.

Option 3:  Combined approach

Both option 1 and option 2 can be used independently to dramatically improve the predictability of DR resources.  But by combining them the resource planner can get a sum that is greater than its parts.  In addition, overlaying the analytics on top of enhanced data collection will likely reduce hardware and communications investments needed in option 1.

Is it all worth the investment?

The equipment and analytics still comes with capital and service costs that need to be taken into account.  Utilities considering one or the other should first conduct an analysis of the market value for enhancing the predictability of its DR programs on a day-ahead and real-time basis.  What are the wholesale market opportunities?  Are we paying for fast response generation services that could be replaced or complemented with more predictable and reliable DR?  These and other questions should be addressed in an assessment study before diving head first into the options above.

For more information about what DNV GL offers, read more here.

3 Comments Add your comment
Will Will says:

Thanks Gino. I agree, there is still plenty of room to improve forecasts in this space.

Avatar Gino Tozzi says:

Hi Will,

It was truly a pleasure to meet you and learn more about the opportunity at DNV. As far as your post, I believe you are correct. There has been tremendous progress made over the last several years with data measurement and collection technologies within the energy sector. This progress will continue into the future with even more sophisticated data collection and measurement techniques. Coupled with the incorporation of advanced modeling strategies to produce more accurate estimates, we should see a continued decrease in the spread between the predicted and actual values. Obviously implementation expenses in the short run and long run will significantly impact the amount of progress made in this direction. I look forward to hearing back from your team and hope you have a nice week.

Best regards,
Gino

Avatar Gino Tozzi says:

Hi Will,

It was really nice to meet you the other day. I read over this blog post more closely and could not agree more with your points. A ±12% margin of error is still sky high compared to other quantities of interest like public opinion polls with a ±3% average margin of error, but it is far better than ±20%. The trend has been and will continue to be improved measurement instruments equating to growing reams of reliable and accurate data. The best and most appropriate analytical techniques will be able to extract more accurate estimates in the future mainly because of accurate data that is handily available as it is produced in such high quantities under all of the circumstances significant enough to be accounted for in demand response. I believe it will be possible to continue increasing the accuracy of those estimates into the future with minimal costs other than the development of even better measurement devices.

Best regards,
Gino

Reply with your comment

Your email address will not be published. Required fields are marked *