Cost Evaluation of Power Engineering based on Improved Particle Swarm Optimization Algorithm

Increased complexity and size of contemporary power engineering projects require more precise and effective cost estimation systems to guarantee optimal resource utilization and project success. Conventional cost estimation systems, however, are plagued with weaknesses such as excessive dependence on historical data, lack of sensitivity towards changing project conditions, and less-than-optimal estimation precision. All these weaknesses translate to budget errors, project schedule variances, and monetary risks. The conventional methods, such as manual approximation, linear programming, and simple heuristic algorithms, are not capable of covering the nonlinear and multidimensional character of power engineering cost factors. To overcome these obstacles, this research introduces a more accurate cost estimation model using an Improved Particle Swarm Optimization (IPSO) algorithm. The new algorithm includes adaptive inertia weight, dynamic learning parameters, and improved velocity update mechanism to avoid premature convergence and improve global search ability. The improved IPSO model accurately handles sophisticated, multi-variable cost functions and provides more accurate and reliable cost estimates than the conventional approaches. Comparative performance is also compared with baseline PSO and other benchmarking procedures for estimation error, convergence rate, and computational cost. Experimental results clearly demonstrate that the IPSO-based model outperforms other methods substantially and provides a robust and intelligent method for power engineering cost estimation problems.