The article proposes a new approach for adjusting the parameters of computing nodes being a part of a data processing system based on analytical simulation of a queuing system with subsequent estimation of probabilities of hypotheses regarding the computing node state. Methods of analytical modeling of queuing systems and mathematical statistics are used. The result of the study is a mathematical model for assessing the information situation for a computing node, which differs from the previously published system model used. Estimation of conditional probabilities of hypotheses concerning adequate data processing by a computing node allows making a decision on the need of adjusting the parameters of a computing node. This adjustment makes it possible to improve the efficiency of working with tasks on the computing node of the data processing system. The implementation of the proposed model for adjusting the parameters of the computer node of the data processing system increases both the efficiency of process applications on the node and, in general, the efficiency of its operation. The application of the approach to all computing nodes of the data processing system increases the dependability of the system as a whole.
Battery Management in a Green Fog-Computing Node: a Reinforcement-Learning Approach
