As Greta Thunberg, the 16-year-old activist environmentalist, said recently after trying in vain to be heard by an international audience at the United Nations, “I will not beg the world leaders to care for our future. I will instead let them know change is coming, whether they like it or not.”
As awareness of climate change grows, one thing has become exceedingly clear: Using energy generated by renewable sources is crucial to reducing harmful greenhouse-gas emissions. And while energy sources like wind and solar are increasingly valuable in this effort, they can be unpredictable and intermittent. How much energy will any single panel or solar plant contribute to the grid on any particular day? The answer to that question has historically been tricky to answer.
Sometimes it’s cloudy. Sometimes the wind doesn’t blow. In order to further rely on the sun and the wind and make the energy they create a bigger part of the grid, we must be able to understand how much power will be available, what the demand for it could be and then use this energy to meet consumer needs as efficiently as possible.
This is where big data comes in. Through an amazing mix of weather data, satellite feeds, predictive analytics and machine learning, we’re entering a future where renewable power can reach the grid on a reliable and much more consistent basis. In fact, the latest forecasting technology may be the missing puzzle piece in the widespread adoption of solar energy.
IBM’s Hybrid Renewable Energy Forecasting solutions (HyREF), for example, uses cloud-imaging technology and sky-facing cameras to predict the weather up to a month in advance. When that kind of technology is used, it can lead to an increase in renewable power generation that is stored or delivered to the grid by up to 10 percent — enough to power 14,000 homes.
Forecasting technology and big data can help solve another challenge, too. Maintaining solar farms — sometimes with hundreds or even thousands of panels spread across large regions — can be a difficult, expensive and sensitive process. Advances in monitoring have made checking on these plants much more efficient.
A company called Extra Space Storage (ESS) uses big data analytics to detect underperformance and identify when inefficiencies occur without having someone on site. The company’s Virtual Irradiance (VI), a solar management program, works by collecting ground level sunlight-intensity data to signal when panels aren’t performing at expected rates, and it sends an alert that repairs or maintenance are needed.
This kind of analysis can even be used to study whole communities and suggest where solar panels could be the most effective based on sun exposure and weather patterns. South Australia, for example, in a collaboration with Tesla, has built the world’s largest virtual power plant, connecting 50,000 Tesla batteries with panels, reducing costs associated with stabilizing the energy grid by $28.9 million. It’s a collaboration that could eventually power the entire state.
The better we can analyze these energy supply-and-demand models, the more a community’s backup energy needs can be accounted for as well. When energy demands are consistently met by renewable sources, companies can reduce their safety margins, which are usually made up of costly and environmentally damaging fossil fuels. This translates to cheaper, more efficient power for both companies and consumers.
As energy prediction becomes more accurate, it’s feasible that associated energy costs with peak usage times — and savings with non-peak usage times — will be passed onto consumers to help control supply and demand. Smart homes could be directed to power down when not in use, incentives could be offered to stay off the grid during certain time periods, and devices such as air conditioners and water heaters can be controlled or turned off remotely.
Solar energy is already a wallet-friendly proposition, but over the next decade, we can expect these kinds of advancements to make solar investment even more attractive. All of these factors should tempt investors who have been reluctant to divert funds to this sector to see its viability and long-term prospects. Companies around the world have recognized the importance of sustainable energy sources, and investment in infrastructure and hardware has increased 20 percent annually since 2014. And last year, renewables accounted for 70 percent of global investment in new power-generation projects.
Big data and machine learning have already begun to revolutionize many industries, from fashion to transportation, and now it’s changing the way we think about and use solar energy. Energy companies, consumers and investors who have all heard the plea for change finally have an answer for how they can harness technological advances to become less a part of the problem and more a part of the solution.
By Daniel Neiditch
Authors propose an iterative cycle of activity that helps companies optimize for both business value and social value in a single business model.
90 Day Finn programme is an intriguing example of how smaller hubs can think outside the box to compete with the San Franciscos, Londons and Singapores of the world.
The lean startup approach for developing new products or businesses has become popular among companies large and small. But is the approach really effective?