Using the precise terminology is a necessary step towards effective communication. As mentioned in my Foresight article "Energy Forecasting: Past, Present and Future", the forecasting practice has a long history in the utility industry, in fact, over 100 years. While load forecasting plays a vital role in many business applications, the usage of different terms is quite messy. Everyone may have his/her own definition of everything in this area. I'm creating a new label "terminology" to host a series of posts on load forecasting terminology. I would like to cover as many ambiguous terms as possible. Here is a tentative list:
- Load, demand, energy and power
- Forecasting and backcasting
- Forecasting and planning
- Forecasting, forecast and forecaster
- Very short, short, medium and long term load forecasting
- Model, variable, function and parameter
- Linear models and linear relationship
- Training, validation and test
- Weather normalization and load normalization
- Prediction interval and confidence interval
- Probability forecasting and probabilistic forecasting
- Reliability (for planning) and reliability (for forecasting)
- Quantile, quartile and percentile
- Resolution (for hierarchical load forecasting) and resolution (for probabilistic forecasting)
- Forecasting and data mining
- Statistical models and econometric models
- Load factor, coincidence factor, diversity factor and responsibility factor
- Calendar month and billing month
- Energy efficiency, demand response and demand side management
- Load forecasting and load research
- Weather, climate and temperature
- Standard time, daylight saving time and local time
- Statistical learning and machine learning
If you can think of other confusing terms, please let me know. I will add the new ones after #12. As I'm moving along, I will also add links to the new posts.
I'm excited to read the posts. Some of the terms listed are definitely difficult to get the hang of. I have a couple of suggestions:
ReplyDeleteMaybe in the context of #2 you could bring up a priori vs. a posteriori.
I would also be interested in better understanding quantiles vs. percentiles, which might fit well in #10 or #11.
Thanks Paul, I added #13 Quantile, quartile and percentile.
ReplyDeleteHere are a few terms that I think could be added to your list:
ReplyDelete1) Planning Year (differs by jurisdiction perhaps?) vs. Calendar Year (obvious)
2) Coincident Peak vs. Non-Coincident Peak
3) Diversified Peak vs. Non-Diversified Peak
Many thanks. Can you elaborate what you mean by planning year?
ReplyDeleteI have added #17 coincidence factor and diversity factor to cover those "peaks" and #18 billing month and calendar month to discuss the unbilled energy issue.
At Newfoundland Power, we forecast demand on a planning year basis because we are a winter peaking utility. For example, the 2013 planning year is from April 1st 2013 to Mar 31 2014...So, for this year's upcoming forecast, I will use actual 2014 planning year peak data to help forecast future years....
ReplyDeleteThank you for your efforts, Dr. Hong. These reviews and comparisons of load forecasting terms are really helpful. I look forward to reading more.
ReplyDeleteit is great effort Dr. Tao, can we add to the list , Forecast vs prediction and estimation
ReplyDeleteThank you Prof.Hong. The list is great. Could you pleade add hierarchical point forecasting and hierarchical probabilistic forecasting to your list?
ReplyDelete