Supercomputers improve solar power forecasts

Sep 30, 2013
Supercomputers improve solar power forecasts
Supercomputers improve solar power forecasts.

To improve the accuracy of solar power forecasting, research meteorologist Edwin Campos and his colleagues at DOE's Argonne National Laboratory have partnered with IBM to build a forecasting technology based on IBM's Watson supercomputer, made famous by its 2011 victory over human champions on the television quiz show Jeopardy!.

Campos hopes that the information he gains by integrating big data processing, machine learning and cloud modeling into a Watson-like platform will help grid managers and power plant operators develop more efficient strategies for allocating their resources to manage the unevenness of solar generation.

"Even five minutes of clouds when we thought there'd be sun can equate to tens of thousands of dollars of extra costs from having to buy other forms of power from across the grid," Campos said. "The more accurately we can forecast clouds, the more money we can ultimately save homeowners on their electric bills."

When a solar plant experiences a generation shortfall, other plants - typically fossil-fuel plants that run on coal and natural gas - need to increase generation in order to make up the difference, or else the grid could experience sporadic outages or even a blackout. These energy sources are relatively less environmentally friendly than solar.
Additionally, grid operators may need to purchase electricity within a short time frame or continually carry additional back-up power in the absence of accurate and timely solar generation forecasts, which can then increase the cost of electricity. These increases are usually passed on to the consumer. With more accurate forecasts, energy can be distributed more efficiently and cheaply.

Explore further: Morocco raises 1.7 bn euros for solar plants

add to favorites email to friend print save as pdf

Related Stories

No more cloudy days for solar

Jun 14, 2012

For a country with so much sunlight, some might think Australia has been slow to adapt its electricity generation mix to include solar power. One of the main reasons for this is solar intermittency.

The grid of the future

Sep 16, 2013

The outlet in your living room doesn't know a lot—yet. Unaware of whether they are drawing power from wind, solar, gas, or coal plants, the electrical lines that bring us power in many ways still resemble ...

Recommended for you

The state of shale

16 hours ago

University of Pittsburgh researchers have shared their findings from three studies related to shale gas in a recent special issue of the journal Energy Technology, edited by Götz Veser, the Nickolas A. DeCecco Professor of Che ...

Website shines light on renewable energy resources

Dec 18, 2014

A team from the University of Arizona and eight southwestern electric utility companies have built a pioneering web portal that provides insight into renewable energy sources and how they contribute to the ...

Better software cuts computer energy use

Dec 18, 2014

An EU research project is developing tools to help software engineers create energy-efficient code, which could reduce electricity consumption at data centres by up to 50% and improve battery life in smart ...

Cook farm waste into energy

Dec 17, 2014

It takes some cooking, but turning farm waste into biofuels is now possible and makes economic sense, according to preliminary research from the University of Guelph.

User comments : 0

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.