Covariance Matrix Adaptation for Multi-objective Optimization
Evolutionary Computation
| Hi-index | 0.00 |
Although, only in recent years, northern European countries started to install large offshore wind farms, it is expected that by 2020, several dozens of far and large offshore wind farms (FLOWFs) will be built in the Baltic, Irish and North seas. These FLOWFs will be constituted of a considerable amount of wind turbines (WTs) packed together, leading to an energy density increase. However, due to shadowing effects between WTs, power production is reduced, resulting in a revenues decrease. Therefore, when FLOWFs are considered, wake losses reduction is an important optimization goal. This work presents a modular approach to optimize the energy yield of FLOWFs through an evolutionary algorithm. In order to do so the algorithm is set to find an optimal WF layout. The method consists of a modular strategy where the site wind rose information is used in different steps, which accelerates the calculation speed of the wake losses. The results presented demonstrate the method effectiveness. A computational time decrease is observed when compared to the standard optimization strategy, without jeopardizing the quality of the optimal layouts achieved.