The paper proposes further development of formal method for obtaining the values of software quality attributes and assessing the quality of software used for controlling and parameters monitoring of autonomous electric power systems. For this purpose, dynamic software testing was used with the involvement of a group of experts. The results of the conducted expert assessment were used as initial data. The attributes of software quality indicators, such as functionality, practicality, maintainability, reliability, were calculated using the method of summarizing and grouping the results of statistical observation that allowed to check the software compliance with quality standards. Additional weighting coefficients that describe the importance of individual software quality attributes were introduced, and additive convolution is used to calculate the values of various software quality indicators. Minimax criterion was used to find the best solution that maximizes the quality of the software and minimizes possible losses due to errors. The technique proposed in the paper makes it possible to obtain quantitative assessments of software quality based on statistical processing of testing results and expert assessments. This allows to select specific software characteristics for improvement without affecting others, to predict software failureless time and to minimize the subjective factor during testing.