Network Management System Research Articles

АДАПТИВНЫЙ МЕТОД И АЛГОРИТМ ОПЕРАТИВНОГО ОЦЕНИВАНИЯ ПАРАМЕТРОВ ТРАФИКА В ВЫСОКОСКОРОСТНЫХ КОРПОРАТИВНЫХ МУЛЬТИСЕРВИСНЫХ СЕТЯХ СВЯЗИ

The article deals with an adaptive method developed and an algorithm that implements it for the rapid evaluation of traffic characteristics and parameters in high-speed corporate multiservice communication networks. This algorithm operates in real-time environment. High-speed corporate multiservice networks are characterized by high dynamics of changing their state, including changes in the characteristics of transmitted traffic. Under these conditions, the automated network management system should provide the required quality of communication services and services provided to users. Thus, the relevance of this study is determined by the need to implement network management processes in a mode close to real time, with a given quality in the conditions of dynamic priority of unknown changes in network characteristics. The basis of the proposed method is the concept of conditional non-linear Pareto - optimal filtering by V.S. Pugachev, which consists in the fact that traffic parameters are estimated in two stages. Firstly, the forecast of parameter values is estimated, and then their correction is made with the following observations of parameters. Traffic parameter forecasts are made in a small sliding window, and refinement of current traffic parameter estimates is implemented by pseudogradient procedures, the parameters of which are regulated by the method of fuzzy Takagi-Sugeno logical output. In this case, increments in pseudo-gradient procedures are calculated relative to the average value of previous estimates calculated in a small moving window as well. This method reduced the average relative error of estimating the intensity parameters of non-stationary network traffic by 1.4-1.9 times, and also reduced the size of the sliding window in which it is processed from 1.7 to 4.2 times.The proposed method and algorithm belong to the class of methods and algorithms which require a preliminary training. The average relative error in estimating traffic parameters does not exceed 7%, which is a sufficient value for the implementation of operational network management tasks.

Intelligent network management system for solving the problem of offline monitoring 5G technologies

Maintenance and management of fourth-generation (4G) current networks are still done manually and semi-automatically, which is expensive and time-consuming. This poses a major challenge for network management of disparate, software-defined, and virtualized fifth-generation (5G) systems. Fifth-generation (5G) cellular networks include a wide variety of technologies to address very different uses. Assessing these technologies and exploring future alternatives is complicated by relying solely on network administrators. 5G network intelligence is an important alternative to network administrators. With the advent of network intelligence for the 5G system opens the possibility of intelligent control. Without the intervention of administrators, the new approach can autonomously solve network problems, cyberattacks and inefficient use of resources, which in turn can reduce operating costs, improve user experience and reduce the time to market of new services. This work presents a test bench of a 5G mobile network with a virtualized and organized structure that focuses on integration into artificial intelligence programs. The presented test bench uses open-source technologies for deployment and orchestration of virtual network functions for flexible creation of various scenarios of mobile networks with clear topologies of frontal and feedback. The article explains how to deploy the structure of the test bench and reproduce the presented results with the provided algorithms and presents the recommended architecture, functionality, closed control, algorithms that include network intelligence. An intelligent 5G test bench has been installed, and experimental results confirm the feasibility and effectiveness.

Directions of legislative and administrative change in the мanagement of motor roads of Ukraine

The state of public highways undoubtedly affects the quality of cargo and passenger transport ation, the level of prices, the degree of employment of the population and the pace of economic development of the state. Consequently, the development of the network management system for highways and improvement of their transport and operational condition is a prerequisite for further socio-economic development of the state and society. Of particular importance are the research directions of the administrative and legal principles of management in the field of motor roads in Ukraine, since the geographical location of Ukraine, subject to the integration of domestic transport infrastructure into the European one, will allow in the future to receive annual international transit transport by road and tourist trips, significant development of international cooperation of the state and significant revenues to the state budget of the country.The article defines the directions of legislative and administrative changes in the management of motor roads of Ukraine.

Design and optimization of integrated energy management network system based on internet of things technology

In recent years, China's economy continues to develop at a high speed, but also faces the enormous pressure of energy shortage and environmental deterioration. As an energy-saving discipline, we should actively adopt advanced energy-saving management methods and technologies for energy utilization management. The purpose of this paper is to study an integrated energy pipeline system based on Internet of things technology. In this paper, the actual data of a university is used to establish a prediction model to predict energy consumption, so as to better carry out energy-saving planning. Based on the theoretical basis of Internet of things technology, combined with the current mainstream technology, windows + Apache + MySQL + PHP as the development environment, ThinkPHP framework as the development framework, and a set of integrated energy data query and energy trend analysis management system. The platform integrates system login, energy consumption data query, historical energy consumption and energy consumption trend analysis, Energy saving report, and provide security and scalable features. The system test shows that the performance of the system designed in this paper is stable and can meet the actual needs. In this paper, four groups of different number of users are simulated. The average response time is less than 5S, and the CPU utilization is less than 70 %.

Automatic System of Illumination of the Territory of the Enterprise

The work is devoted to the development of an intelligent lighting control system for adjacent territories.Every day more and more popular is the use of led lamps, they are more economical from outdated gas-discharge lamps or incandescent lamps, which are now commonly used. For comparison, a 40W incandescent lamp has a luminous flux of 400 lumens, the same luminous flux has a 5W led lamp. There are many outdoor lighting network management systems that have a wide range of management capabilities. The most common ones are LonWorks, DMX-512, DALI, DCI. They usually use motion sensors, light sensors, time relays, and other automation elements, each of which has its own advantages and disadvantages. These advantages and disadvantages have been analyzed in terms of application in the system being developed. The main requirements for the system were economic and ease of use. Taking into account these requirements, the existing methods of street lighting management and systems based on them were considered.A block diagram of the lighting control system for the adjacent territories of the enterprise was developed, which is shown in figure Fig. 1. The system is a network whose nodes are connected by a simple digital data bus DB. The digital data bus can be wired, wireless, or optical. Each network node consists of: an MSi motion sensor, an LLi led lamp, a microcontroller with a built-in MCi real-time clock, a light-sensitive LSI sensor, and IUI interface blocks. The light-sensitive sensor can be installed in one place, provided that the level of natural light in the coverage area of each local lighting system is approximately the same. When the level of external natural light decreases below a certain critical level, the light-sensitive sensor sends a signal to the microcontroller to turn on the local lighting system, after which each local zone is illuminated with individual specified parameters of the glow power. When the motion sensor is activated in the local area of the lighting system, the lamp switches to high power mode. Thanks to a real-time microcontroller, the moment when an object appears in this zone is recorded. As the object moves, it enters the coverage area of another local lighting system where the network uses a built-in real-time clock to record the moment when the object appears in another zone, this information is transmitted via a digital bus to the system, from which we can determine the direction of movement of the object.Based on the developed block diagram and based on the requirements for the system being developed, a microcontroller from the STM family was selected. This family of microcontrollers, due to their performance, architecture and low power consumption, is best suited for working with the hardware of the system being developed.

CALCULATION OF THE EFFEC TION OF THE EFFECTIVENESS OF THE FUNC TIVENESS OF THE FUNCTIONING TIONING OF MULTISERVICE COMMUNICA VICE COMMUNICATION NE TION NETWORKS T WORKS TAKING IN AKING INTO ACCOUNT DROPPED P T DROPPED PACKETS

Background. The article discusses the formalization of performance indicators of a multiservice network management system based on the use of hybrid neural-fuzzy technology that combines the advantages of fuzzy logic and neural networks. A developed fuzzy neural model was subsequently used to make a decision about the transfer of real time streams through the channel of the multi-servo network. Methods for assessing the effectiveness of multiservice communication networks can be conditionally divided into three large groups: technical, economic and technical and economic. As the technical characteristics of the efficiency of the computer network, various indicators of network performance and reliability are used. Estimates of the costs of designing, installing and maintaining the network are used as economic characteristics. Technical and economic indicators are used for a comprehensive assessment of the project, and include various combinations of technical and economic characteristics. The response time is an integral performance characteristic, the most important for the network subscriber.

SYNTHESIS OF DATA COLLECTION METHODS BY TELECOMMUNICATION AIRPLATFORMS IN WIRELESS SENSORS NETWORKS

Background. Wireless sensor networks using telecommunication airplatforms for monitoring data collection belong to the class of complex, multifunctional, dynamic systems. To increase the efficiency of functioning of this class of networks, it is necessary to develop methods that allow achieving various target functions of network management: increase the time of network functioning, reduce the time of data collection, minimize the resources consumed. An integral part of the wireless sensor network management system is the subsystem of control over data collection from nodes using telecommunication airplatforms. When managing the process of data collection there are scientific tasks: finding the minimum number of points (nodes) of data collection, building the shortest flight routes of these points, defining flight strategies, ensuring the quality ofdata exchange, increasing the time of network operation. At present, there are no effective methods and algorithms to solve these scientific problems. This article is dedicated to the synthesis of methods that solve these problems.Objective. The purpose of the paper is development and improvement of monitoring data collection methods from wireless sensor network nodes on the basis of motion and positioning control of telecommunication air platforms.Methods. The analysis of initial data was performed and the main stages for synthesis of monitoring data collection methods by telecommunication airplatforms in wireless sensory networks were considered. The following mathematical models are proposed: clustering of wireless sensors networks; estimation of network nodes power consumption; time of data collection; quality of monitoring data collection and transmission. The algorithms of search of position and movement of telecommunication airplatforms for achievement of the given control objectives at monitoring data collection are improved.The effectiveness of the proposed methods of monitoring data collection has been assessed.Results. The results of simulation modeling showed that using the proposed models and algorithms in the implementation of monitoring data collection methods from nodes using telecommunication airplatforms allows: reducing data collection time by 15-20%; increasing network operation time by 10-15%; reducing the required number of telecommunications airplatforms to 15%.Conclusions. The synthesized methods make it possible to: determine the position and trajectory of telecommunication airplatforms when optimizing various target functions; perform real-time control; plan the trajectory of telecommunication airplatforms; improve the efficiency of algorithmic and mathematical support of network control system.

AIT: An AI-Enabled Trust Management System for Vehicular Networks Using Blockchain Technology

Currently, connected vehicles have gradually stepped into our daily lives, and they generally rely on vehicular networks to generate and exchange traffic-related messages to improve the overall travel safety and efficiency. However, due to the open nature of vehicular networks, these traffic-related messages could be erroneous, which may be caused by various reasons, ranging from an onboard device (OBD) sensor malfunctioning and reporting incorrect reading to the message being tampered by a malicious vehicle. To address these rapidly increasing security challenges, we have proposed an AI-enabled trust management system (AIT) in this article, which is an AI-enabled trust management system for vehicular networks using the blockchain technique. In the AIT system, each vehicle first senses, generates, and exchanges messages with other vehicles. These messages then get validated by the neighboring vehicles. As vehicles receive and validate messages from other nearby vehicles, they will establish and manage the trust of those nearby vehicles, which is enabled by utilizing the deep learning algorithm. Once a vehicle identifies untrustworthy vehicles, it reports them to the nearby roadside unit (RSU), and the RSU will validate the authenticity of the report as well as the identity of the vehicle by using the emerging blockchain technique. The security credentials of untrustworthy vehicles will then be revoked by the RSU. We have conducted an extensive experimental study to evaluate the AIT system. Simulation results clearly indicate that AIT performs better than existing approaches and can manage the trust of vehicles and detect malicious ones in an accurate and efficient manner.

Formalization of requirements for the telecommunications network management system

Formalization of requirements for the telecommunications network management system

IMPLEMENTASI NETWORK MANAGEMENT SYSTEM ( NMS ) MENGGUNAKAN PANDORA FMS DI PT. SAMUDRA MARINE INDONESIA

PT. Samudra Marine Indonesia (SMI) has a network where all users are connected to one computer, and a computer (server) with a network concept like this can affect the performance of RAM, processors and hard drives, due to frequent occurrence of computers on computer users always slow and the hard disk capacity is starting to full sometimes there are also computers that suddenly disconnect from the network. However, the IT technician does not know what is happening to the user's computer because the IT technician room is very far away from the SMI 2 building due to different buildings.So we need a system with the concept of Network Management System (NMS) which functions as a supervisor for the state of the server computer or client computer so that it can be handled quickly. The Network Manage-ment system (NMS) network uses the Linux Centos operating system which will be installed using the Pandora FMS application. Methods: 1. Study 1: conducting experiments (designing) .2. Study 2: analysis and design of Network Management System.The results show that the Pandora FMS application runs in accordance with the research objectives, the us-er to the server can access the Pandora FMS software. Hard disk, RAM and Processor have been efficient in monitoring performance at PT. Samudra Marine Indonesia.

Supervised and Semi-Supervised Learning for Failure Identification in Microwave Networks

Automated failure-cause identification in communication networks allows operators to reduce service unavailability. Once the most likely failure root-cause is identified, appropriate countermeasures can be effectively put in place (e.g., by choosing an in-field intervention vs. a remote equipment reconfiguration). In this article, we describe a successful application of Machine Learning (ML) for automatic failure identification in microwave networks based on the real-field data. On microwave links, different heterogeneous causes (e.g., adverse atmospheric conditions, or obstacles) lead to service unavailability and produce not easily-distinguishable degradation effects on the transmission parameters. Hence, failure identification is traditionally accomplished by domain experts via direct inspection of transmission-parameter logs. As a first contribution, we identify six categories of failure causes in microwave networks and show that supervised ML enables very accurate failure identification, hence significantly simplifying failure troubleshooting. Comparing various ML algorithms, we find that up to 93% classification accuracy is obtained using real-field labeled datasets with 2513 points. One main hindrance to the application of supervised learning is that, in real network deployments, limited amount of labeled data is available for training, as manual labeling is performed by domain experts based on their knowledge and experience. On the other hand, collecting unlabeled data is relatively simple as network management systems retrieve large amounts of unlabeled information automatically. As a second contribution, we investigate an automated labeling procedure, based on autoencoders-like Artificial Neural Networks, to combine the knowledge of the few manually-labeled data with large unlabeled data. Results show that our data augmentation based on autoencoders can slightly improve failure-cause identification only when Artificial Neural Networks or Support Vector Machines are used, while accuracy slightly decreases when adopting Random Forest.

METHODS OF CORPORATE INFORMATION SYSTEM MANAGEMENT ON THE BASIS OF OPTIMAL CONTROL THEORY

To manage corporate information systems that include a large number of active equipment, you need complex systems that monitor, control and manage each element and state of the system as a whole. Finding the optimal delineation of both the functions of the central part of the SU and the management functions of the autonomous segment, and the actual division into autonomous segments is important because it directly affects the efficiency of management. The question of the optimal management of the information system as a whole is still unresolved. Therefore, the development of a method of information system management using the theory of optimal control is appropriate and relevant. For corporate information systems, optimal management should provide a minimum criterion of optimality under given constraints. That is, the minimum cost of control (control signals in the form of protocols). It should also be borne in mind that not every optimal solution, synthesized theoretically, can be implemented in practice on the basis of the existing prior art. The theory of automatic optimal control in its traditional forms cannot be the only basis of the network management system. It should be integrated with other promising areas, such as artificial intelligence systems and a methodology for describing complex under-formalized systems. The method of corporate information system management based on the theory of optimal management assumes that the first stage in the sequence of receiving, storing and processing information in the system is the stage of determining (recognizing) the state using image recognition methods. The next stages of the proposed method are the formation of a strategy for optimal management, development and implementation of management actions based on it using existing protocols. On the basis of the developed method the general structural scheme of SU by the information system consisting of several autonomous segments is offered and protocols for its realization are resulted and defined.

Command filtered finite-time control for nonlinear systems with state constraints and its application to TCP network

This work studies the issue of finite-time tracking control for a class of nonlinear systems with state constraints. By means of command filtered backstepping technique, finite-time theory and Barrier Lyapunov Functions (BLF), a novel finite-time command filtered backstepping approach is presented to guarantee the finite-time convergence of tracking errors. The new proposed method can not only reduce the complexity of computation of the conventional backstepping control and compensate filtered errors by Dynamic Surface Control (DSC), but also can guarantee that the state variables are restricted in compact bounding sets. Moreover, the proposed controller is designed and applied to Transmission Control Protocol/Active Queue Management (TCP/AQM) network systems, which guarantees the practical boundedness of all the signals in the closed-loop system. Finally, the effectiveness and practicability of the developed control strategy are validated by a TCP network simulation example.

Flow-based anomaly intrusion detection using machine learning model with software defined networking for OpenFlow network

Moving towards recent technologies, Software Defined Networking (SDN) produces a promising network framework to combine the overall network management system with network programming. It gives a more effective tracking system towards the data center. By centralized system and symmetric controller, it prevents security cracks from creating new threats during OpenFlow packet transmission with vulnerabilities. It creates more interest to the researchers to work towards Flow-based SDN for the priority-driven algorithm in anomaly intruder detection. In this paper, we made a study towards a priority-based model using SDN to control the flow of data packets over the network, gives assurance to the bandwidth enforcement, and reallocation is made through virtual circuits. The network behavior of the system is continuously monitored through the machine learning model for normal and abnormal traffic data transmission to detect anomaly intruders. Flow-based machine learning (ML) model with SDN act as an intelligent system to limits the throughput virtually through the flow of reserved bandwidth and make use of extra bandwidth, which presents more than the utilization bandwidth for priority-based applications with minimal cost while compared with the traditional methods. The proposed work also compared with the schemes available at the network to produce outcomes with fast routing and the fault tolerance of existing networks to overcome the gap open at the security of the SDN architecture to detect and identify vulnerabilities.

Design and application of intelligent monitoring and management system for campus weak current pipeline network based on IoT+GIS technology

In view of the characteristics and problems in the process of information construction and operation of the campus weak current pipeline network, combined with the actual needs of the development of smart campus, an intelligent monitoring and management system of the weak current pipeline network based on IoT+GIS technology is designed and the campus geospatial information database as well as the weak current pipeline network database are established at the same time. The three-dimensional visual integration management of weak current communication resources, such as underground pipeline laying, optical fiber routing analysis, fiber-optic fusion relationship, integrated wiring in the building, off-motion monitoring of well cover, and so on, is realized, which greatly improves the campus weak current pipeline network resources management and maintenance efficiency, and provides scientific decision-making basis for rational and effective use of these resources.

Bayesian bootstrap quantile regression for probabilistic photovoltaic power forecasting

Photovoltaic (PV) systems are widely spread across MV and LV distribution systems and the penetration of PV generation is solidly growing. Because of the uncertain nature of the solar energy resource, PV power forecasting models are crucial in any energy management system for smart distribution networks. Although point forecasts can suit many scopes, probabilistic forecasts add further flexibility to an energy management system and are recommended to enable a wider range of decision making and optimization strategies. This paper proposes methodology towards probabilistic PV power forecasting based on a Bayesian bootstrap quantile regression model, in which a Bayesian bootstrap is applied to estimate the parameters of a quantile regression model. A novel procedure is presented to optimize the extraction of the predictive quantiles from the bootstrapped estimation of the related coefficients, raising the predictive ability of the final forecasts. Numerical experiments based on actual data quantify an enhancement of the performance of up to 2.2% when compared to relevant benchmarks.

Machine Learning assisted aggregation schemes for optical cross-connect in hybrid electrical/optical data center networks

Making optical circuit switching suitable for handling highly dynamic and profoundly changing traffic is a considerable challenge. This motivation drives the development of a hybrid electrical/optical network towards high bandwidth and low latency. Compared with the traditional non-aggregation scheme, we provide two machine learning assisted aggregation schemes. The first one is to design optical cross-connect switches to increase the throughput of the circuit-switched network. In this solution, the optical cross-connect serves both delay-sensitive traffic flows and delay-tolerant traffic flows. As the network throughput rises rapidly, the number of ports of the optical switch remains unchanged. The second scheme is to add small port counts, which maximizes throughput while relaxing the requirements for accurate machine learning algorithms. In this paper, we have a set of four machine learning algorithms, and only the most suitable one is selected at a time. We deploy a machine learning algorithm at edge nodes instead of a central network management system. Therefore, we can simultaneously reduce network overhead and latency. Both aggregation schemes outperform the traditional non-aggregation scheme in terms of throughput, delay, and flow completion time.

Neural Network Management System for the Robot on the base of Raspberry Pi

Neural Network Management System for the Robot on the base of Raspberry Pi

Optimization of Computer-aided Teaching Network Management System for College Physical Education Courses

Optimization of Computer-aided Teaching Network Management System for College Physical Education Courses

A Simulator for Reporting Performance Data from Network Element To Network Management System

Now a days, the biggest challenge for Mobile Network Operators is to provide broadband service with high performance.4G(VoLTE) has been developed to meet user requirement by offering high speed data transfer services using IMS network. The key performance indicators (KPI) are used to monitor and optimize mobile network performance in order to provide high quality services using counters. The indicators are standardized by third-generation partnership project(3GPP). Simulators are used in network element so that we can check the capacity of each VM and calculated using counters from element management system to network management system.