The solar industry’s low-tech problem and how to fix it

Kirk Edelman, chief commercial officer at New York City-headquartered solar development, construction, and asset management company Safari Energy, told Electrek about the three technologies that the solar industry needs to adopt in order to revolutionize processes and infrastructure.

Many solar companies began as startups that cobbled together whatever processes and software they could afford to handle everything from origination to accounting. They often grew by focusing on finding cheaper, more efficient equipment. 

The Solar Energy Industries Association and Wood Mackenzie predicted that US solar capacity will increase by a multiple of four this decade.

Edelman explained to Electrek what tech he thinks the US solar industry needs, and why, in order to keep up with the growing demand for solar power:

Artificial intelligence

Millions of variables and data points impact the efficacy of panels from shading to soiling. Parsing and developing insights from these data points requires an investment in artificial intelligence. AI enables increased automation, reduces human error, and can free up time to arrive at insights otherwise unattainable.

For example, AI is being used at Safari Energy to evaluate complex commercial and industrial (C&I) rooftops. An AI algorithm can identify rooftops, determine ideal solar panel size and placement, and even accurately calculate system costs, savings, and investment returns. This method easily surpasses human analysis both in terms of speed and accuracy and can be used to rapidly analyze real estate portfolios of hundreds of properties to identify priorities.

What this all means is that if you’re considering solar for your business, a company that utilizes AI can provide an estimate that is an order of magnitude more accurate in seconds compared to days when done manually.

AI can also eliminate repetitive, error-prone tasks, avoiding confusion and delays in areas from bill analysis to proposal creation. This also frees up employees to focus on more sophisticated and creative work.

Machine learning

Machine learning further amplifies the benefits of AI by continuously improving the algorithms used. By feeding a program with real-world data and reference cases, it can recognize patterns and self-correct, thereby improving accuracy.

For example, some C&I rooftops might be different shades of color depending on the materials used. An algorithm might initially confuse a dark-colored roof with asphalt on the ground or even a body of water. By showing the algorithm-specific examples, it can recognize nuanced differences and incorporate its findings into future models.

As a result, solar companies that use machine learning to continually improve their algorithms can further improve the accuracy of their proposals while reducing the burden of having employees focused on time-consuming tasks.

Data analytics

Put simply, solar companies must incorporate robust analytics into their operations. By tracking and analyzing the data they create to find weaknesses in their equipment and operations, companies can de-bottleneck resources to maximize production out of existing equipment and improve daily operations. 

One area where data analytics can be applied is setting an organization’s strategic focus. Often, we have seen solar companies that rely almost entirely on instinct or inertia to determine which companies would be good targets. However, when you apply sophisticated analytics such as empirical data, regression analysis, heat maps, and scoring models (to name a few), it is possible to more effectively determine which geographies, industries, and company’s metrics represent the most potential and should be targeted.

This area requires an investment in technology and personnel who can interpret and make decisions on the data produced, and a cultural shift so that an organization is agile enough to make large-scale decisions supported by their new data analytic capabilities. Otherwise, companies run the risk of falling into the big data trap, with lots of information, but no practical way to use it.

The above technological advancements create opportunities for further enhancements, like digital twinning, which involves creating digital models of real solar equipment to run simulations on the degradation over the lifespan of that equipment. Using this preventive maintenance concept, companies can predict when their equipment will fail and replace in advance, averting any costly disruptions. 

 Kirk Edelman is chief commercial officer at Safari Energy. He joined Safari Energy following a 12-year career with Siemens, where he most recently served as president and chief executive officer of Siemens Financial Services, Inc. as well as CEO of the Global Energy Finance business. Kirk is a board member of Cornell University’s Program in Infrastructure Policy, the German American Chamber of Commerce, and New Jersey Institute of Technology’s Martin Tuckman School of Management.

Subscribe to Electrek on YouTube for exclusive videos and subscribe to the podcast.