CASE STUDIES | SOLAR PANEL OUTPUT PREDICTION | OPTIMIZATION
The interest of green energy continues to grow as more and more consumers look for alternative ways to power their homes and businesses. Solar power companies rely on warm, sunny days to produce optimal amounts of energy for their customers. In order to meet the demands of their clients, and understand their data, one confidential client looked to Quantar for help. Their question was this: “How can AI machine learning data analysis help my business? Can I predict the power output daily yield of my solar panels based on ambient temperature, irradiation (direct sun expose), and module temperature, all of which are weather-dependent?” It should also be noted that daily yields of power output vary from panel to panel, based on conditions such as panel age, damage level, placement, and maintenance schedule. The client approached us asking if it was possible to use AI to predict the output of their solar farm based on the data they had.
Data values were taken and recorded every 15 minutes for a total of 34 days. These values included, date, time, panel ID, ambient temperature, module temperature, irradiation percentage, and total power yield. These data values, or metrics were entered onto a spreadsheet and uploaded to Quantar’s Data Science software. Quantar’s proprietary software enables clients to ask Natural Language questions to predict future outcomes.
By using Quantar’s NLP (Natural Language Program), the client was able to analyze cumulative and individual solar power data and based on those metrics, predict power output on estimated weather expectations. This data enabled them to understand where their maintenance was insufficient, what days were expected to produce lower output so they could optimize storage, and where and how much new solar arrays to build. It gave them deeper insights into how their solar arrays were running than they had ever seen before. Just by asking the question.
AI is a great opportunity for businesses to take advantage of the relatively recent and massive proliferation of data. According to McKinsey, AI has the potential to deliver additional global economic activity of around $13 trillion by 2030, or about 16% higher cumulative GDP compared with today. AI and machine learning are examples of tools that businesses can utilize to make sense of what is known as “Big Data” (data sets too large or complex to be dealt with by traditional data-processing software). But many companies, particularly small and medium-sized ones, have faced challenges adapting to the technology wholesale. These include a deficiency in technical skills required to utilize AI, a lack of understanding of its benefits or uses, or difficulty in defining a strategy and finding an appropriate use-case for the technology. It is vital to have a clear picture of what you want to achieve with an AI project; much like a jigsaw puzzle, you need to know what the result is supposed to look like before you start putting pieces together. Machine learning tools can analyze large datasets to identify patterns or make predictions. Examples include Natural Language Processing applications that can analyze social media posts to see what customers are saying about a brand or tailored sales promotions for customers. These insights allowed for targeted messaging, increased sales and ultimately a deeper insight than ever before of how a product or technology is being used. Quantar can help with every stage of this analysis and bring the power of Machine Learning and AI into your hands. Contact Quantar today.
How AI helped revolutionize a solar panel company by predicting the optimal output
Using historical data and forecasting tools to improve ecommerce sales
Realize efficiencies by reducing costs and anticipating future market directions