Spacecraft solar arrays degradation forecasting with evolutionary designed ANN-based predictors

The problem of forecasting the degradation of spacecraft solar arrays is considered. The application of ANN-based predictors is proposed and their automated design with self-adaptive evolutionary and bio-inspired algorithms is suggested. The adaptation of evolutionary algorithms is implemented on the base of the algorithms´ self-configuration. The island model for the bio-inspired algorithms cooperation is used. The performance of four developed algorithms for automated design of ANN-based predictors is estimated on real-world data and the most perspective approach is determined.