Monday, September 29, 2014

Forecasting and Backcasting

Forecasting is the process of exploring the future events that have not been observed or determined. Backcasting "typically" refers to the process of exploring the past events given the information known to date. The two terms seem to be mutually exclusive, but are often used in an ambiguous way.

Friday, September 26, 2014

Load, Demand, Energy and Power

Let me start with the easy pair, power and energy. Power is the amount of energy consumed over time, while energy is the integral of power over time. In the electric power industry, the most frequently used units of power are kW (kilowatt) and MW (megawatt): 1MW = 1000kW = 1,000,000W. Consequently, the common units of energy are kWh (kilowatt hour) and MWh (megawatt hour). 

There are three types of power in an AC (alternating current) power system: active power or real power (in W, watt), reactive power (in Var, volt-ampere reactive) and complex power (in VA, volt-ampere). The magnitude of complex power is called apparent power (in VA). See Wikipedia for more details about AC power

Wednesday, September 24, 2014

Weather Station Selection for Electric Load Forecasting

In the load forecasting literature, most papers are focusing on the direct application of some techniques, such as regression, ARIMA, ANN, etc. Not many papers are discussing original methodologies that can be used across different techniques. The investigation on new sub-problems of load forecasting is even rare. Weather station selection is a necessary step in load forecasting, but has never been formally studied in the past many decades. We wrote this paper last year to describe how to apply a greedy method and out-of-sample test to select weather stations. Although regression models are used here, our methodology is independent of the techniques as long as they rely on weather variables.

The paper was accepted by International Journal of Forecasting this summer. The working paper is available HERE. I will update the citation once the paper is on Science Direct.

Citation
Tao Hong, Pu Wang and Laura White, "Weather Station Selection for Electric Load Forecasting", International Journal of Forecasting, accepted, working paper available from http://www.drhongtao.com/articles.

Weather Station Selection for Electric Load Forecasting

Tao Hong, Pu Wang and Laura White

Abstract

Weather is a major driving factor of electricity demand. Selection of weather station(s) plays a vital role in electric load forecasting. Nevertheless, minimal research efforts have been devoted to weather station selection. In the smart grid era, hierarchical load forecasting, which provides load forecasts throughout the utility system hierarchy, is becoming an emerging and important topic. Since there are many nodes to forecast in the hierarchy, it is no longer feasible for forecasting analysts to manually figure out the best weather stations for each node. A commonly used solution framework is to assign the same number of weather stations to all nodes at the same level of the hierarchy. This framework was also adopted by all of the four winning teams of Global Energy Forecasting Competition 2012 (GEFCom2012) in the hierarchical load forecasting track. In this paper, we propose a weather station selection framework to determine how many and which weather stations to use for a territory of interest. We also present a practical, transparent and reproducible implementation of the proposed framework. We demonstrate the application of the proposed approach to forecasting electricity at different levels in the hierarchies of two US utilities respectively. One of them is a large US generation and transmission cooperative that has deployed the proposed framework. The other one is from GEFCom2012. In both case studies, we compare our unconstrained approach with four other alternatives based on the common practice mentioned above. We show that the forecasting accuracy can be improved by releasing the constraint on the fixed number of weather stations.

Saturday, September 20, 2014

Inside Leaderboard

The first evaluation week (Task 4) of GEFCom2014 just went by. CrowdAnalytix publishes the leaderboard based on the best score of each team in real time. Since some teams made multiple submissions, that leaderboard won't reflect the real positions. To enhance the transparency of our scoring process, I manually pulled the submission log of each track to come up with a more realistic leaderboard. Please understand that:

Thursday, September 11, 2014

Towards Winning GEFCom2014 - Six Must Read Recommendations before Evaluation Period Starts

GEFCom2014 had a super strong start. Within the first 4 weeks, we have had 225, 138, 126 and 135 solvers in the load, price, wind and solar tracks respectively. Totally 345 people have joined the LinkedIn group Global Energy Forecasting Competition. While many winning teams of GEFCom2012 came back to GEFCom2014 with very strong performance, several new faces also topped some of the tasks. Having been monitoring the competition from the back end, I am so excited about the ups and downs on the leaderboards. I really wish I could join the game in person.

The evaluation period of GEFCom2014 is starting in less than 2 days. I'd like to offer some recommendations, so that the contestants fully understand what makes a winning solution. Some of them may be overlapping with my previous post, GEFCom2014 is ON - 8 Tips before You Join the Game, but I think it's important to cover them again here.

Monday, September 8, 2014

I'm Hiring AGAIN, for BigDEAL

I have been building my lab since joining UNC Charlotte last year. I named the lab "BigDEAL", for Big Data Energy Analytics Laboratory. Over the past 12 months, the BigDEAL has attracted more than $2.5M of donations and research funding from 5 industry donors and 9 project sponsors. The members of the BigDEAL have completed three projects and is currently working on three other projects. For more information, please visit the BigDEAL webpage.


Now I'm hiring again, for BigDEAL.

Sunday, September 7, 2014

Load Forecasting Terminology: 32 Terms in 12 Posts

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:
  1. Load, demand, energy and power
  2. Forecasting and backcasting
  3. Forecasting and planning
  4. Forecasting, forecast and forecaster 
  5. Very short, short, medium and long term load forecasting
  6. Model, variable, parameter and function
  7. Linear models and linear relationship
  8. Training, validation and test
  9. Weather normalization and load normalization
  10. Prediction interval and confidence interval
  11. Probability forecasting and probabilistic forecasting
  12. Reliability (for planning) and reliability (for forecasting)
  13. Quantile, quartile and percentile
  14. Resolution (for time series data) and resolution (for probabilistic forecasts)
  15. Forecasting and data mining
  16. Econometric model and statistical model
  17. Coincidence factor and diversity factor
  18. Billing month and calendar month
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. 

Tuesday, September 2, 2014

Job Opening at SCE: Senior Integrated Demand Analysis and Forecasting Planner

Posting a job for SCE. The position is in the same team as the previous SCE jobs I posted here. If you are interested, you can search through SCE job site using the job number 71008358. Alternatively, you can search under "Senior Integrated Demand Analysis and Forecasting Planner". The posting will be up and open until Sept. 10th.

Monday, September 1, 2014

IIF Student Forecasting Awards for Energy Analytics

Today is Labor Day. Thanks to the International Institute of Forecasters (IIF), I received my first Labor Day gift, an email notification of the IIF student forecasting award for five years.

While the interested readers can get the details from the IIF website, here are a few highlights:

  • The awards are offered by the IIF to the top-performing students in undergraduate and graduate level forecasting courses. 
  • No more than 20 awards are available across all universities. 
  • No more than one subject can be eligible for an IIF award at the same university. 
  • Each star student will receive $100, a Certificate of Achievement from the IIF, and one year’s free membership of the Institute, with all its attendant benefits. 

Friday, August 15, 2014

GEFCom2014 is ON - 8 Tips before You Join the Game

After one full year of planning and implementation, I'm pleased to announce that the Global Energy Forecasting Competition 2014 is ON. Please visit CrowdANALYTIX.com to look for the four tracks.

For now, I will defer all the thanks to the end of the competition. (BTW, it will have to be a long thank-you letter, because so many people have devoted so many days and nights to set up this competition.) Instead, I would spend my last sleepless night before the competition to provide a few tips and instructions to the GEFCom2014 contestants: