An Adaptive Model-Based Mutation Operator for the Wind Farm Layout Optimisation Problem

Abstract

A novel mutation operator for the wind farm layout optimisation problem is proposed and tested. When a wind farm layout is simulated, statistics such as an individual turbine's wake free ratio can be computed. These statistics are in addition to the global measure being optimised, for example the overall cost of energy extraction of the farm. We present algorithms that first of all build a predictive model of the wake free ratio across an entire wind farm. This model is then used inside a mutation operator to perturb turbines towards positions of high predicted wake free ratio. We evaluate our approach by comparing a 1+1 Evolutionary Strategy using this new mutation operator vs. the same algorithm with a more standard random mutation operator, and show that our new operator leads to the discovery of wind farm layouts having a statistically significantly lower cost of energy extraction.

BlockCopy-based operators for evolving efficient wind farm layouts

“…In contrast, other approaches (e.g. [14]) treat the optimiser as a "white box" and use intermediate values in the cost computation to provide a search bias. However, such approaches are unfair if compared directly to black box approaches, and so we leave a white box variant of BlockCopy for future work.…”