Smart Meter Data Analytics
(status: ongoing, people involved: X. Liu, L. Golab, W. Golab, I. Ilyas, S. Jin)
In this project, we are building and benchmarking a scalable data management system for collecting and mining smart meter data, including electricity and water meters. The proposed system will compute typical consumption profiles from the data, cluster consumers according to their consumption habits and detect outliers. Our research focus in this project is threefold: 1) implementing existing data mining algorithms in an efficient and scalable way and 2) proposing new algorithms for understanding and extracting useful information from smart meter data, and 3) visualizing the results in a user-friendly manner.
Modelling the Effects of Weather for Impact Analysis of Pricing Policies
(status: ongoing, people involved: R. Miller, L. Golab, C. Rosenberg)
Analyzing the impact of pricing policies such as time-of-use (TOU) is challenging in the presence of con- founding factors such as weather. In this project, we are developing a methodology for modelling the effect of weather on residential electricity demand. We consider coincident weather measurements such as windchill, the delay between when an outdoor temperature occurs to when its effects are felt within a home, and the non-linear relationship of temperature with demand. We also apply our methodology to evaluate the effect of mandatory TOU pricing using a smart meter dataset of over 20,000 households.
Predicting Peak Aggregate Demand
(status: completed, people involved: Y. Jiang, R. Levman, L. Golab, J. Nathwani)
Peak reduction is an important problem in the context of the electricity grid and has led to conservation programs in various jurisdictions. For example, in Ontario, residential customers are charged higher prices during peak times, while large industrial and commercial customers pay heavy surcharges that depend on their load during Ontario’s five peak-demand days. Reducing these surcharges is a challenging problem for large consumers due to the difficulty of predicting peak days in advance. Using demand forecasts and actual demand data from the IESO, we analyzed the difficulty of predicting peak-demand days and peak hours on those days. We found that even the state-of-the art peak-prediction algorithms require consumers to curtail load ten or more times, and even then, they may not identify all five peak-demand days.