Automatic Load Model Selection Based on Machine Learning Algorithms

Technology development and decentralized operations create changes in conventional electric systems, where load modeling has been a challenge dynamic analysis. Consequently, accurate models are required to ensure the quality of studies current systems. This paper presents an automatic strategy based on clustering, classification, optimization algorithms, obtain case several system operating conditions. The obtained can be helpful for planning operation power proposed approach validation is performed using IEEE 14-bus test system, high performance obtained. average cross-validation error assigned 13 clusters disturbances 5.36 × 10-3. used as tolerance value determine when online model suitable represent measured disturbance. tests show strategy’s capabilities defining online, making this field applications.