Saturday, October 25, 2014

Probability Forecasting and Probabilistic Forecasting

Probabilistic energy forecasting is an emerging branch of energy forecasting. I think it's very important to clarify some concepts in the early stage, so that we don't have to run into troubles arguing what the terms mean 10 years later. This post is about probability forecasting and probabilistic forecasting.

Wednesday, October 22, 2014

Weather Normalization and Load Normalization

In the electric power industry, there are two variables often associated with "weather normalization": reliability and load. If you are interested in reliability, you may refer to the activities of IEEE Working Group on Distribution Reliability. In this post, I'm going to focus on load.

Planning - the business driver of weather normalization

Job Opening at TXU Energy: Statistical Modeling Sr. Analyst

Posting a job for a friend at TXU Energy. If you are interested, please apply HERE.

Statistical Modeling Sr. Analyst (17926)

Requisition Id 17926 - Posted 10/01/2014 - Accounting / Finance - TXU Energy - IRVING, TX

This is a sophisticated Senior Statistical Modeling Analyst position.


Tuesday, October 21, 2014

Training, Validation and Test

When developing models for forecasting or data mining (I will write a post about these two terms), we usually slice the data into three pieces, training, validation and test:
  • Training data is used to estimate the parameters. 
  • Validation data is used to select models. 
  • Test data is used to confirm the model performance. 
Here let me use two representative techniques, regression analysis and Artificial Neural Networks (ANN) to illustrate how the process works.

Monday, October 20, 2014

BigDEAL Students Winning Poster Contest of Analytics2014

I'm fortunate to be the father of two adorable kids, Leo and Angela. I remember their first cry, first smile, first "ba-ba" (means Daddy in Chinese) and first crawl. Since my wife has told me many times "no more kids", I guess I have to live with only two kids.

Last month, my first PhD student, Bidong Liu, forwarded me an email from the conference chair of Analytics2014, saying that his poster had won the poster contest of Analytics2014. As a winner, Bidong was invited to Las Vegas to present the work "how does temperature affect electricity demand" with the trip covered by the conference. To make the deal even sweeter, I also sent him to the post conference training "Forecasting Using SAS Software: a Programming Approach" taught by Dr. David Dickey.

Bidong Liu @Analytics2014
While Bidong is the lucky guy getting the treat, the poster is the result of teamwork of several engineering students. The second author is Jiali Liu, another BigDEAL student. She is getting her Master of Science degree in Engineering Management next semester. Her thesis topic is on combining load forecasts. If you are trying to fill your analyst position(s), I highly recommend that you check out her profile.

Now I realize that I have more than two kids: the BigDEAL students are bringing me the joyful moments too, after they have survived through all the tough days under my supervision of course.

Thank you BigDEAL students, and congratulations Bidong!

Saturday, October 18, 2014

Linear Models and Linear Relationship

In many papers, we can find the statements similar to the one below:
Because linear models can hardly capture the nonlinear relationship between load and temperature, we use Artificial Neural Networks (or other black-box models) in this paper. 
The major conceptual error of the above statement is due to a common misunderstanding that linear models cannot capture nonlinear relationship.

Wednesday, October 15, 2014

Model, Variable, Function and Parameter

My first job was an engineer at an expert-based consulting firm. One of my first tasks was to develop models for a large Investor Owned Utility. I was quite exited when being assigned to this project - I thought it was a good opportunity to show off my modeling skills. During the project kick-off meeting, I realized that I misunderstood the scope of work. The "models" I was asked to develop are circuit models. "Modeling" was simply to draw the lines, fuses, switches and transformers on a distribution engineering software platform based on their physical specifications, which did not involve any math or statistics at all.

The predictive models in energy forecasting are different from the physical models mentioned above. A regression-based load forecasting model, for example, describes the relationship between load and the factors that drive the load. There are three components in such a model:

Job Opening at Tucson Electric Power: Manager of Customer Analytics

Posting a job for a friend at Tucson Electric Power. If you are interested, please file your application through THIS LINK.

Manager, Customer Analytics

Company: Tucson Electric Power
Location: Tucson, AZ
Job Category: Finance
Position Type: Unclassified

Tuesday, October 14, 2014

A Survey on Software Packages for Load Forecasting

I'm preparing a report on load forecasting for National Association of Regulatory Utility Commissioners (NARUC), which will be published by the U.S. Department of Energy as a white paper in 2015. In one of the sections, I'd like to include a wide range of tools and solutions that are being used in practice. Although the case study is on long term load forecasting, I would be happy to include some contents about tools and solutions for short term forecasting as well.

Now I need your help to make this section as valuable as possible. If you are interested in contributing to this white paper, please send me your response by Oct 31, 2014.

Vendors in load forecasting space, please send me a 1-2 page non-commercial description of your product offerings, which should include, but is not limited to:

  • A general overview of the company and your load forecasting products
  • Pros and cons of the products and information about future enhancements
  • Your customer base, i.e., number of customers and major customers
  • References to your technical resources, such as journal/conference papers and white papers, etc.

Utility load forecasters, please kindly let me know by either sending me an email (hongtao01 AT gmail DOT com) or replying to this post:

  • Your name and affiliation 
  • Your main job duties relevant to load forecasting
  • Tools and/or solutions you are using and your opinions about them (SAS, EViews, Itron, Matlab, MS Excel, R, or else?).
If you are tired of writing long emails, I can call you to take notes during the interview. I will acknowledge the ones who have provided the materials that are used in the final report. If you don't want your name to appear in a public document, please let me know as well.

Friday, October 10, 2014

Very Short, Short, Medium and Long Term Load Forecasting

Load forecasting is so fundamental that it is being used across all sectors in the electric power industry for various business applications. Because of the wide spread of its applications, there are many ways to classify the various load forecasts:
  • based on forecast horizon: very short, short, medium and long term load forecasts;
  • based on resolution of the data or updating frequency (these two concepts are different!): hourly, daily, monthly, seasonal and annual load forecasts;
  • based on business needs: operational, planning and retail load forecasts;