scholarly journals Software product to reduce commercial energy losses

2020 ◽  
Vol 178 ◽  
pp. 01082
Author(s):  
Maksim Vladimirovich Borodin ◽  
Tatyana Anatolievna Kudinova ◽  
Zumeyra Munirovna Shakurova
Keyword(s):  
Real Time ◽  
Energy Losses ◽  
Electric Grid ◽  
Electricity Theft ◽  
Software Product ◽  
Commercial Energy

The personnel of electric grid companies spend considerable amount of time searching for noncontractual and non-meteredelectricity consumption. The raids carried out by personnel of electric grid companies to detect electricity theft are not always effective, as they are carried out selectively and often do not take into account many factors that could affect the number of detected cases of electricity theft. The article proposes a software product that allows, on the basis ofconsumers’ registration, who have already stolen electricity, have arrears in payment for consumed electricity, made uncontrolled consumption, carry out a process of technological connection or have non-meter accounting, to send personnel conducting a raid to identify electricity theft. It also makes possible to generate the necessary acts, certificates, etc.in real time, which allows staff to reduce the time to fill out paper versions and transfer the necessary documents to the police. The software product allows to increase the efficiency of raids by electric grid companies, by reducing the time of inspections. In turn, the implementation of the proposed software product will allow electric grid companies to significantly reduce energy losses by increasing the territoriality of raids.

Recognition and calculation of objects in images using YOLOv3 architecture

2021 ◽  
Vol 26 (jai2021.26(2)) ◽  
pp. 42-53
Author(s):  
Hrabovskyi V ◽  
◽  
Kmet O ◽  
Keyword(s):  
Real Time ◽  
High Speed ◽  
High Reliability ◽  
Fruit Trees ◽  
Learning Technology ◽  
Visual Objects ◽  
Software Product ◽  
Different Types ◽  
Original Classification ◽  
Trained Network

Program that searches for five types of fruits in the images of fruit trees, classifies them and counts their quantity is presented. Its creation took into account the requirement to be able to work both in the background and in real time and to identify the desired objects at a sufficiently high speed. The program should also be able to learn from available computers (including laptops) and within a reasonable time. In carrying out this task, the possibilities of several existing approaches to the recognition and identification of visual objects based on the use of convolutional neural networks were analyzed. Among the considered network archi-tectures were R-CNN, Fast R-CNN, Faster R-CNN, SSD, YOLO and some modifications based on them. Based on the analysis of the peculiarities of their work, the YOLO architecture was used to perform the task, which allows the analy-sis of visual objects in real time with high speed and reliability. The software product was implemented by modifying the YOLOv3 architecture implemented in TensorFlow 2.1. Object recognition in this architecture is performed using a trained Darknet-53 network, the parameters of which are freely available. The modification of the network was to replace its original classification layer. The training of the network modified in this way was carried out on the basis of Transfer learning technology using the Agrilfruit Dataset. There was also a study of the peculiarities of the learning process of the network under the use of different types of gradient descent (stochastic and with the value of the batch 4 and 8), as a result of which the optimal version of the trained network weights was selected for further use. Tests of the modified and trained network have shown that the system based on it with high reliability distin-guishes objects of the corresponding classes of different sizes in the image (even with their significant masking) and counts their number. The ability of the program to distinguish and count the number of individual fruits in the analyzed image can be used to visually assess the yield of fruit trees

scholarly journals Intelligent system for monitoring the air pollution of the city in real time

2019 ◽  
Vol 2 (1) ◽  
pp. 579-588 ◽  
Author(s):  
Mykhailo Lobur ◽  
Krzysztof Pytel ◽  
Uliana Marikutsa ◽  
Dmitrij Korpyljov
Keyword(s):  
Air Pollution ◽  
Real Time ◽  
Intelligent System ◽  
Software Product ◽  
Visualization Systems ◽  
A Site ◽  
User Friendly ◽  
The City ◽  
Theoretical Foundations

Abstract The article reveals the theoretical foundations, types of pollutants, classification of monitoring and visualization systems of air pollution. A description of the design of the structure of the system is described, its components are described in detail, and the justification of the selected technologies is given. In general, the system consists of two parts: a device for collecting air pollution data and a site that displays these data in user-friendly form. Graphic images that display the appearance of a software product are also added.

A Software Product Line Design Based Approach for Real-time Scheduling of Reconfigurable Embedded Systems

2021 ◽  
Vol 115 ◽  
pp. 104925 ◽  
Author(s):  
Hamza Gharsellaoui ◽  
Jihen Maazoun ◽  
Nadia Bouassida ◽  
Samir Ben Ahmed ◽  
Hanene Ben-Abdallah
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Software Product Line ◽  
Product Line ◽  
Product Line Design ◽  
Real Time Scheduling ◽  
Software Product ◽  
Time Scheduling ◽  
Line Design

Proposed An Intelligent System for Electricity Theft Detector at Smart City Scenarios

2016 ◽  
Vol 5 (1) ◽  
pp. 51
Author(s):  
Syifaul Fuada
Keyword(s):  
Real Time ◽  
Intelligent System ◽  
Electrical Power ◽  
Distribution Transformer ◽  
Output Current ◽  
Control Center ◽  
Electricity Theft ◽  
Current Usage ◽  
Intelligent Security ◽  
Phase Differences

<p class="Abstract">This is a conceptual proposal which is aimed at describing an intelligent security system to early detect cases of electricity theft which is claimed effective to cope with ICT based cases of electrecity theft. The method employed in the detector is computation system, which is the computation of phase differences (Φ), current voltage in real time and losses detection of electrical power grid by 220V. The losses calculation employs Kirchoff’s law I which is Kirchoff’s current law. The current sensors are put on the output distribution transformer and on customer’s APP connection. The working principles are (1) reading output current and phase differences at the load point (of the customer’s) in the distribution transformer using the current sensor, (2) comparing the output current (I<sub>o</sub>) with the sum of certain variables on consumers to be discussed in this paper. (3) Knowing the data of electric current usage by recording data of losses in real time and by sending them to teh control center monitoring in in real time.</p>

Sign in / Sign up

Export Citation Format

Share Document