In this paper, the architecture of hybrid analog radio over fiber (ARoF) and next-generation (NG) wavelength division multiplexed passive optical network (WDM-PON) infrastructure for broadband internet services and the latest fifth-generation (5G) cellular mobile communications is proposed. Investigated ARoF-WDM PON architecture is a trade-off between technology and cost for future 5G mobile cellular communications to meet the internet service requirements, allowing to increase system capacity ensuring higher spectral and energy efficiency. In our proposed infrastructure the widespread used passive optical access network (PON) architecture is technologically transformed to the AROF-WDM-PON transmission system without replacing existing network elements, by integrating baseband units (BBUs) or mobile radio transmitters located in optical line terminal (OLT) at the central office (CO) and the receiving radio unit (RU) part of mobile base stations, leaving the traditional WDM-PON broadband architecture unchanged. In our investigated ARoF-WDM PON transmission system model, designed in the simulation environment, we research the possible ARoF system implementation scenarios into the PON’s segment, which has been now standardized to the 40 Gigabit-capable next-generation passive optical network (NG-PON2) standard providing an unique solution for hybrid fiber optical infrastructure serving as the next step for future 5G wireless communication networks.

The main topic of the article is accuracy evaluation of supervised machine learning algorithms performance applied to real network traffic data. The main task to be solved by supervised learning is classification of video traffic type - streaming (real-time) video or on-demand video (a record). The experiment has been performed for the same video fragment with data filtering and without it. The results have been summarized in form of tables with accuracy assessment for multiple commonly used supervised machine learning algorithms.

The paper is dedicated to the numerical and experimental study of nonlinear oscillations exhibited by the Vilnius chaotic generator. The motivation for the work is defined by the need for a comprehensive analysis of the dynamics of the oscillators being embedded into chaotic communication systems. These generators should provide low-power operation while ensuring the robustness of the chaotic oscillations, insusceptible to parameter variations and noise. The work focuses on the investigation of the dependence of nonlinear dynamics of the Vilnius oscillator on the operating voltage and component parameter changes. The paper shows that the application of the Method of Complete Bifurcation Groups reveals the complex smooth and non-smooth bifurcation structures, forming regions of robust chaotic oscillations. The novel tool—mode transition graph—is presented, allowing the comparison of experimental and numerical results. The paper demonstrates the applicability of the Vilnius oscillator for the generation of robust chaos, and highlights the need for further investigation of the inherent trade-off between energy efficiency and robustness of the obtained oscillations.

This article represents a new method of collection and processing of meteorological data of meteorological service. This operation is based on observations and correction of numerical weather forecast errors by using a new algorithm. This algorithm considerably increases the accuracy of the short-term forecast of external air temperature. The algorithm providing correction of predicted air temperature within the next three hours is considered. Processing of temperature data using Kalman Filter provides the decrease in predicted temperature errors. The work also describes practical use and implementation of accuracy improving algorithm of predicted temperature by using Python.

To improve the quality of control of the engineering systems of the building this work provides intellectual management system to increase energy efficiency. This work describes a new method of designing management systems to control buildings' engineering systems capable to inform on the negative influence of different control algorithms on energy efficiency. This new method uses the weather forecast processed by Kalman's filter. Hot water supply valve in the heat node is used as the test bed for the offered structure of control. This intellectual system was developed in the Python programming language. This intelligence control system also equips error detection in engineering systems of the building.

These days, the high-quality live video streaming platforms are very widely used by lot of people all over the world. The demand for such services has increased even more in current pandemic conditions, so it is important to maintain certain level of Quality of Service for live streaming video. This article aims at pre-processing live streaming video-traffic packets for Deep Learning application of classification of different quality mode (Resolution and framerate) based only on statistical properties of network traffic Internet Protocol (IP) packets flow. The traffic intensity is used as a main traffic type descriptor with some additional transforms. The article presents some of classification accuracy analysis depending on multiple factors, such as: type of traffic pre-processing, length of traffic window, traffic intensity sampling time. The results show that there is a set of such parameters that leads to the best classification accuracy. This way, it may be possible for content operators (platforms) to provide differentiated services for their users. According to testing results, for Deep Learning application the direct traffic intensity samples allows achieving good accuracy of 94% and higher without any additional transforms. This, of course, depends on the classifier model parameters, and article provides insight into them as well.