Determination of weight coefficients for additive fitness function of genetic algorithm

The paper presents a solution for the problem of choosing a method for analytical determining of weight factors for a genetic algorithm additive fitness function. This algorithm is the basis for an evolutionary process, which forms a stable and effective query population in a search engine to obtain highly relevant results. The paper gives a formal description of an algorithm fitness function, which is a weighted sum of three heterogeneous criteria. The selected methods for analytical determining of weight factors are described in detail. It is noted that expert assessment methods are impossible to use. The authors present a research methodology using the experimental results from earlier in the discussed project “Data Warehouse Support on the Base Intellectual Web Crawler and Evolutionary Model for Target Information Selection”. There is a description of an initial dataset with data ranges for calculating weights. The calculation order is illustrated by examples. The research results Программные продукты и системы / Software & Systems 1 (33) 2020 53 in graphical form demonstrate the fitness function behavior during the genetic algorithm operation using various weighting options. The analysis of the results implies that it is more preferable to calculate fitness function weight factors for this query population then using the results of all population queries. The conclusion is based on the presence of successive improvements in query populations which reflect the correct operation of genetic algorithms, as well as on the obvious detection of local and global maxima in the fitness function during experiments. When using other methods of calculating weighting factors there is no such thing. Thus, a method for determining weight factors for an additive optimality criterion can improve genetic algorithm quality to generate effective search queries. In particular, the probability of rapid detection of fitness function local extremes is increased and this local extreme can become the optimal solution the function domain.