The interest in the utilization of offshore wind power is increasing significantly worldwide. A typical offshore wind farm may have hundreds of generators, which are outspread in the range of several to tens of kilometres. Therefore, many feasible schemes exist for the wind turbine location and internal line connection in a wind farm. The planner must search for an optimal one from these feasible schemes, usually with a maximum wind power output and the lowest installation and operation cost. 

Wind farm control has been a research topic for more than two decades. It has been identified as a core component of grand challenges in wind energy science to support accelerated wind energy deployment and to transition to a clean and sustainable energy system for the 21st century. The prospect of collective control of wind turbines in an array to increase energy extraction, reduce structural loads, improve the balance of systems, reduce operation and maintenance costs, etc., has inspired many researchers to propose innovative ideas and solutions over the years. However, practical demonstration and commercialization of some of the more advanced concepts have been limited by a wide range of challenges, which include the complex physics of turbulent flows in wind farms and the atmosphere, uncertainties related to predicting structural load and failure statistics, and the highly multi-disciplinary nature of the overall design optimization problem, among others.

One of the major problems that is being faced at wind farms is rising bird fatalities due to wind turbines. A study held in 2012 shows that bird strikes led to nearly 366000 bird deaths in the US alone. A firm in Colorado has found a solution to this problem. A company named IdentifFlight uses AI to remedy the situation by reducing bird fatalities by up to 85%.

AI for bird safety

IdentiFlight uses ML and AI software to identify birds flying towards windmills and curtail turbines if a collision is inbound. According to their website, Curtailment criteria are ultimately defined by the operator and are highly configurable.

The company has seen 150 installations globally in 5 countries, with millions of positive detections. Duke Energy’s Top of the World Wind Power project saw an 82 per cent decrease in eagle collisions with little to no loss in efficiency, claims the firm.

IdentiFLight leverages a combination of industry-leading proprietary software and algorithms, wide-field-view cameras and high-resolution stereoscopic cameras to provide real-time bird detection and tracking with extremely high accuracy. Machin vision and a neural network allow it to classify the birds. IdentiFlight data utilizes AI techniques to optimize the balance between risk and conservation.

The work of such firms is critical to faster acceptance of wind energy.