By: Farid Najafi, president of Arbox Renewable Energy.
The concept of artificial intelligence (AI) involves machines learning and acting on data sets without human programming or intervention. AI can be broken down into machine learning, deep learning and neural networks.
Without getting too technical, essentially the whole premise of AI is a machine mimicking the human brain. The machine can learn and adapt to different scenarios, and as times passes the machine, gets smarter and reacts differently to achieve better results.
AI will play a pivotal role in many industries, through business intelligence and solving problems quicker than humans. Solar is no exception.
AI in frequency regulation
In North America power is produced at frequency of 60 Hz AC. This means the direction of the current changes 60 times per second. With the growth of renewables coming onto the grid, keeping the frequency in its tolerable band (close to 60 Hz) has been challenging for grid operations. This is because renewables such as wind and solar are intermittent sources of power.
Traditionally gas turbines and coal generation plants have been used to keep the frequency stable, but they are slow to respond. Now operators are looking at faster responding options, such as battery storage, to maintain grid frequency and avoid outages. This is creating an opportunity for AI to help.
Generally a human has to look at power supply and demand and adjust control of distributed resources to keep everything balanced. But because demand and supply change frequently, sophisticated AI can learn data patterns from smart meters better than humans to understand cause and effect—along with other factors such as weather, season, time and region—to predict when additional power resources are needed and for now long.
AI in weather forecasting
AI can also be useful in weather forecasting. Accurate weather forecasting helps utilities make smart decisions about operations in severe weather conditions such as hail, thunderstorms and hurricanes. AI can analyze large volumes of historical and real-time data from satellites, weather stations and IoT devices to recognize patterns and predict weather that could impact solar production. This information can allow power producers to adjust accordingly.
AI to optimizing project performance
AI also can be used to maximize performance of power plants. For instance, if you have 10 power plants in your portfolio, maybe eight are performing at 90% and two at 85%. AI can analyze data—region, system, slopes, humidity, irradiance, manufacturer—to recognize anomalies or issues that a human may not.
Furthermore, AI can be used for predictive maintenance by learning algorithms to spot inconsistencies and determine when a panel or an inverter is about to fail.
Whats coming next?
AI will increasingly automate operations over the next several years in the solar and wind industries and boost efficiencies across the renewable energy sector, according to a recently released DNV GL paper, Making Renewables Smarter: The benefits, risks, and future of artificial intelligence in solar and wind.
“We expect the installation of more sensors, the increase in easier-to-use machine learning tools, and the continuous expansion of data monitoring, processing and analytics capabilities to create new operating efficiencies—and new and disruptive business models,” said Lucy Craig, director technology and innovation at DNV GL – Energy.
According to the paper, solar and wind industry stakeholders will see artificial intelligence benefits in several areas, including:
-Robotics growing in prevalence for remote inspection, with new benefits in maintenance and troubleshooting.
-Crawling robots that can get close to a structure’s surface enabling a new set of technologies such as microwave and ultrasonic transmitters and receivers, which can be used to penetrate structures to reveal faults in materials.
-Supply chain optimizations by autonomous driving robots, which can in future build entire onshore wind or solar farms: parts of a wind turbine or a solar array are transported from the factory by self-driving lorries, unloaded by another set of robots, attached to the foundations that yet other robots have dug and filled, and pieced together by a final set of robots and drones.
-Autonomous drones with real-time artificial intelligence-supported analysis will become the primary tool for carrying out effective and efficient inspections of wind turbines and solar panels.
-AI applications accelerating due diligence, reducing the time investment of planning and analysis that today requires many human hours.
“Solar and wind developers, operators, and investors need to consider how their industries can use it, what the impacts are on the industries in a larger sense, and what decisions those industries need to confront,” co-author Elizabeth Traiger concluded.
Farid Najafi is the president of Arbox Renewable Energy. Arbox specializes in asset management software in the solar industry