Research on Optimization Method of Power Audit Sample Sampling Based on Hybrid Optimization Algorithm

Audit sampling refers to the methodology wherein auditors select a subset of samples from the audit population for testing, subsequently inferring population characteristics based on the results. A critical challenge emerges in obtaining sufficient, reliable, and valid audit evidence under stringent constraints of limited budget and time, while fulfilling audit objectives and mitigating sampling risks. This study aims to address these challenges through the Hybrid Adaptive Dynamics (HAD) algorithm. By investigating the mathematical model of sample sampling in power audits, this research develops a hybrid optimization algorithm that synergistically combines the strengths of diverse algorithms. Through empirical validation with simulated data and comparative analysis against Genetic Algorithm, Simulated Annealing, and Particle Swarm Optimization, the findings demonstrate that the HAD algorithm significantly enhances sample coverage in power audit sampling under constrained resources. The proposed algorithm provides a more effective technical approach for power audit sampling, thereby contributing to improved audit efficiency and quality.