The short term load forecasting plays a significant role in the management of power system supply for countries and regions, in particular in cases of insufficient electric energy for increased needs. A back-propagation artificial neural-network (BP-ANN) genetic algorithm (GA) based optimizing technique for improved accuracy of predictions short term loads is proposed. With GA's optimizing and BP-ANN's dynamic capacity, the weighted GA optimization is realized by selection, crossing and mutation operations. The performance of the proposed technique has been tested using load time-series from a real-world electrical power system. Its prediction has been compared to those of obtained by only back-propagation based neural-network techniques. Simulation results demonstrated that the here proposed technique possesses superior performance thus guarantees better forecasting.

Since early eighties, not too many happened in analytical methods of performance valuation for actual computer and communication networks. The methods of the classic queuing theory (the mean value analysis, the convolution method) adopt unrealistic assumptions. The stochastic queuing network methods are not adequate for investigation of actual networks. Therefore, the paper presents an approximate method based on many-year performance evaluation experience and some heuristics. The approach is based on the notion of the closed route within the computer network under investigation; the complete network being described as a collection of such closed routes. The method was successfully validated by simulation and measurements. Some more complex approximations, feasible due to development of the computing tools, are also proposed.

In societal applications of systems science where competition under conflicting interests is pertinent to, the decision making faces situations in which one must decide whether to cooperate or not with a competitor or opponent. Each of the opponents (‘players’) has as well as carries own missions within the society out. At least two if not more parties need to make decisions under fully or partially conflicting objectives when involved in a dispute or open conflict. By and large decisions must be made under risk, uncertainty, and incomplete or fuzzy information implying large amounts of linguistic and probabilistic information. For cases of two opponents, the synergy of fuzzy control approach and matrix games seems rather effective to represent and find solutions for such multi-criteria conflicting situations. The fuzzy procedure is used to take into account some of the subjective attitudes of the decision makers that are difficult to model using classical game theory.