Department of Mechanical Engineering, M.A.N.I.T, Bhopal, India.
Environ Sci Pollut Res Int. 2023 Jul;30(31):77436-77452. doi: 10.1007/s11356-023-27849-7. Epub 2023 May 31.
The placement and configuration of wind turbines (WTs) are the key factors in determining the performance and energy output of a wind farm (WF). This involves considering various elements such as wind speed, wind direction, and the interspacing between turbines in the design process. To achieve an optimized and consistent wind farm layout optimization (WFLO) for maximum output power, a novel hybrid algorithm hybrid particle swarm optimization and genetic algorithm (HPSOGA), combining particle swarm optimization (PSO) and genetic algorithm (GA), is proposed. HPSOGA can effectively handle problems with multiple local optima, as PSO explores multiple regions and GA refines solutions found by PSO. The framework has two phases, where PSO improves initial parameters in the first phase, and parameters are adjusted in the second phase for improved fitness. The wake effect is analyzed using the Jenson-Wake model, and the objective function considers the total cost of WTs and the power output of the WF. The interspacing of WTs is evaluated by the rule of thumb. HPSOGA outperforms other methods such as GA, BPSO-TVAC, L-SHADE, BRCGA, and EO-PS, producing better results in terms of total output power generation. The simulation results validate the reliability of HPSOGA in WFLO.
风力涡轮机 (WT) 的布置和配置是决定风电场 (WF) 性能和能量输出的关键因素。这涉及到在设计过程中考虑风速、风向和涡轮机之间的间隔等各种因素。为了实现最大输出功率的优化和一致的风电场布局优化 (WFLO)，提出了一种新的混合算法——粒子群优化和遗传算法的混合 (HPSOGA)，它结合了粒子群优化 (PSO) 和遗传算法 (GA)。HPSOGA 可以有效地处理具有多个局部最优值的问题，因为 PSO 可以探索多个区域，而 GA 可以优化 PSO 找到的解决方案。该框架有两个阶段，在第一阶段 PSO 改进初始参数，在第二阶段调整参数以提高适应度。使用 Jensen-Wake 模型分析尾流效应，目标函数考虑了 WT 的总成本和风电场的功率输出。WT 之间的间隔通过经验法则进行评估。HPSOGA 在总输出功率方面优于 GA、BPSO-TVAC、L-SHADE、BRCGA 和 EO-PS 等其他方法，产生了更好的结果。仿真结果验证了 HPSOGA 在 WFLO 中的可靠性。
