Smart-meter data could improve the performance and efficiency of national power grids

February 7, 2017, King Abdullah University of Science and Technology

Power generators face the constant challenge of matching the amount of power produced at any given time with the demand from consumers. Excess generation is wasteful and expensive, while undergeneration can cause brownouts. For this reason, accurately predicting power demand hours or even days in advance is critical for the reliable and sustainable operation of the electricity grid.

Saudi Arabia's King Abdullah University of Science and Technology (KAUST) Distinguished Professor of Applied Mathematics and Computational Science Marc Genton and his colleagues have developed an effective way to use the enormous amount of -usage data reported by household energy meters to more accurately forecast power demand.

In many countries, households and businesses are fitted with "smart" power meters that report power consumption in short intervals to the electricity network. For consumers, smart meters make it possible to monitor electricity usage in real time, and often the data they collect can help to identify usage habits and issues. For generators, smart-meter data represent a potential gold mine of information with which to better predict demand and operate power-generation facilities more efficiently. However, the sheer volume and complexity of data collected by household smart meters on a city or regional scale makes using the data challenging.

"Smart-meter data can help generators understand individual electricity consumption behavior," explained Genton; "however, the heterogeneity, high level of noise and volume of data require the development of new forecasting algorithms. Our flexible machine-learning algorithm is designed to handle the specific properties of smart-meter data."

One of the main difficulties in effectively analyzing household power-consumption data is the noise caused by rapid changes in energy usage as appliances are switched on and off. In addition, the enormous variety in usage patterns among households and the volume of data that need to be analyzed presents tremendous obstacles for traditional analytical approaches.

Genton and his former postdoc Souhaib Ben Taieb and KAUST Assistant Professor of Applied Mathematics and Computational Science Raphaël Huser collaborated with Professor Rob J. Hyndman from Monash University in Australia to develop a machine-learning algorithm that computes one-day-ahead probabilistic forecasts for each meter using recent time-series data and many predictor variables, including date and weather parameters. In their demonstration study, the team used the distributed computing environment at KAUST to analyze half-hourly smart-meter data recorded by more than 3,000 households over 1.5 years.

"Our algorithm has many advantages, including flexibility, automatic variable selection and interpretability," said Genton, "and we showed that it can provide more accurate probabilistic forecasts compared to existing state-of-the art forecasting methods."

Explore further: Google's PowerMeter Will Help Reduce Energy Consumption (Video)

More information: Souhaib Ben Taieb et al. Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression, IEEE Transactions on Smart Grid (2016). DOI: 10.1109/TSG.2016.2527820

Related Stories

The flexible grid involves its users

September 27, 2016

The GreenCom project, funded in part by the European Commission and led on the technical side by Fraunhofer FIT, ended after 42 months, judged a resounding success. The project's main result is a Smart Energy Monitoring and ...

When hackers turn out the lights

September 16, 2016

The development of the smart power grid and the smart meter in our homes to accompany it brings several benefits, such as improved delivery and more efficient billing. Conversely, any digital, connected technology also represents ...

Taking charge in electricity research

July 7, 2014

Dr Rebecca Ford, from the School of Engineering and Computer Science, is part of a nationwide research team exploring the future of electricity supply and consumption in New Zealand.

Recommended for you

A novel approach of improving battery performance

September 18, 2018

New technological developments by UNIST researchers promise to significantly boost the performance of lithium metal batteries in promising research for the next-generation of rechargeable batteries. The study also validates ...

Germany rolls out world's first hydrogen train

September 17, 2018

Germany on Monday rolled out the world's first hydrogen-powered train, signalling the start of a push to challenge the might of polluting diesel trains with costlier but more eco-friendly technology.

Technology streamlines computational science projects

September 15, 2018

Since designing and launching a specialized workflow management system in 2010, a research team from the US Department of Energy's Oak Ridge National Laboratory has continuously updated the technology to help computational ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.