Pavel Matrenin

TL;DR: In this article , a model of medium-term forecasting of load graphs for electric power system (EPS) with specific properties, based on the use of ensemble machine learning methods is proposed.

TL;DR: It was shown that the accuracy and generalization properties of small-size recurrent models can be significantly improved by the proper selection of the hyper-parameters and training method, and the effectiveness of the proposed approach was validated using a real-case dataset.

TL;DR: In this paper, a model for medium-term forecasting of water inflow for planning electricity generation, taking into account climatic changes in isolated power systems, was proposed using an approach based on machine learning methods, which are distinguished by a high degree of autonomy and automation of learning.

TL;DR: In this article , a simulation model and software have been implemented to perform simulations and calculate the economic efficiency of a wind turbine with and without a hydrogen storage device, based on three-year real data of wind speeds and electricity tariffs in the Novosibirsk region and Krasnodar Territory (Russian Federation).

TL;DR: The Particle Swarm Optimization and the Bees Algorithm were applied to solve the problem of the compensation units power control as a dynamic optimization problem, considering the possible stochastic failures of the Compensation units.