The goal of this paper is to demonstrate the power of machine learning and deep learning combined with powerful tools used in creating virtual simulations. This is made possible by the Unity Game Engine, a software used for the development of 2D and 3D video games and simulations, and the ML-agents plugin, which contains algorithms for training intelligent agents. The basic principles and algorithms of Deep Learning are described. Agent uses these methods to perceive the environment and solve certain tasks. In this paper, a simulation is created in which the agent tries to find hidden objects using machine learning. When the agent finds an item, a new location for the item is randomly generated. It must also complete the task in a specified amount of time. With the right implementation and parameters, the agent could successfully complete the task.
This paper presents an analysis of the harmonic influence of an electric vehicle charging station (EVCS) on the harmonic distortion of the voltage in a low-voltage (LV) distribution network. The analysis was performed by simulations of harmonic power flows for different sources of harmonic distortion. In the first case, the source of harmonic distortion is existing non-linear loads in the 0.4 kV network. In the second case, EVCS is added, and in the third case, the photovoltaic power plants are added as another harmonic distortion source. Input data on harmonics for the 0.4 kV network and EVCS were obtained by measurements in the real life and input data for the harmonic influence of the photovoltaic power plants is taken from the literature. The results of the simulations indicate the possibility of deteriorating the power quality when analyzing the joint impact of EVCS and photovoltaics.
Video encoding nowadays mostly revolves around optimizing and modifying existing encoders. Popular encoders such as H.264 and H.265 have open source implementations, and researchers oftentimes modify only certain parts of the encoder to obtain desired results. In this work, several 4K raw drone videos will be analyzed in regard to spatial and temporal complexity, which could be used for encoder optimization. In the last few years, drones have gained in popularity and their use cases have expanded. Drone racing and filmmaking evolved from being only hobbies, and today there are professional drone racers and filmmakers. Hence, drone video transmission systems must keep pace with industrial demand. It is known that scene complexity affects encoding quality. Specifically, spatial information (SI) and temporal information (TI) can be calculated in various ways and depending on SI and TI score, video bitrate must be increased/decreased in order to sustain the desired quality level.
