Set Of Different Tasks Research Articles

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing

Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy. To enhance data efficiency by sharing parameters across multiple tasks, a common practice segments the network into distinct modules and trains a routing network to recombine these modules into task-specific policies. However, existing routing approaches employ a fixed number of modules for all tasks, neglecting that tasks with varying difficulties commonly require varying amounts of knowledge. This work presents a Dynamic Depth Routing (D2R) framework, which learns strategic skipping of certain intermediate modules, thereby flexibly choosing different numbers of modules for each task. Under this framework, we further introduce a ResRouting method to address the issue of disparate routing paths between behavior and target policies during off-policy training. In addition, we design an automatic route-balancing mechanism to encourage continued routing exploration for unmastered tasks without disturbing the routing of mastered ones. We conduct extensive experiments on various robotics manipulation tasks in the Meta-World benchmark, where D2R achieves state-of-the-art performance with significantly improved learning efficiency.

Decision making in open agent systems

AbstractIn many real‐world applications of AI, the set of actors and tasks are not constant, but instead change over time. Robots tasked with suppressing wildfires eventually run out of limited suppressant resources and need to temporarily disengage from the collaborative work in order to recharge, or they might become damaged and leave the environment permanently. In a large business organization, objectives and goals change with the market, requiring workers to adapt to perform different sets of tasks across time. We call these multiagent systems (MAS) open agent systems (OASYS), and the openness of the sets of agents and tasks necessitates new capabilities and modeling for decision making compared to planning and learning in closed environments. In this article, we discuss three notions of openness: agent openness, task openness, and type openness. We also review the past and current research on addressing the novel challenges brought about by openness in OASYS. We share lessons learned from these efforts and suggest directions for promising future work in this area. We also encourage the community to engage and participate in this area of MAS research to address critical real‐world problems in the application of AI to enhance our daily lives.

Wireless Home Automation System Using IOT and Node MCU Learning

Abstract: The Internet of Things commonly known as IOT (Internet of Things), refers to any device that can be connected to Internet and further controlled using it. Home Automation Systems(HAS) involves the control and automation of lighting, ventilation, security. A wireless home automation system is developed in way that a different set of tasks are performed automatically. This system allows one to wirelessly control lights, fans, air conditioners, television sets, security cameras, etc.

Point estimate observers: A new class of models for perceptual decision making.

Bayesian optimal inference is often heralded as a principled, general framework for human perception. However, optimal inference requires integration over all possible world states, which quickly becomes intractable in complex real-world settings. Additionally, deviations from optimal inference have been observed in human decisions. A number of approximation methods have previously been suggested, such as sampling methods. In this study, we additionally propose point estimate observers, which evaluate only a single best estimate of the world state per response category. We compare the predicted behavior of these model observers to human decisions in five perceptual categorization tasks. Compared to the Bayesian observer, the point estimate observer loses decisively in one task, ties in two and wins in two tasks. Two sampling observers also improve upon the Bayesian observer, but in a different set of tasks. Thus, none of the existing general observer models appears to fit human perceptual decisions in all situations, but the point estimate observer is competitive with other observer models and may provide another stepping stone for future model development. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Гонка нанометров: американская политика в отношении Тайваня и Республики Корея

Intensive development of manufacturing capabilities of Taiwan and Republic of Korea (RoK) since 1960s leads to their emergence as key global semiconductor asset. Until 2020/2021 TSMC and Samsung supplied almost 100% of most technologically advanced chips. The U. S. considered this situation as critical dependence – both for political (conflict with China, securitization of digital technologies, etc.) and economic reasons (risks of supply distortions). Along with science and technology (S&T) efforts major accent was put on new relations with Taiwan and RoK as sources of investments and competences needed to regain U.S. capabilities. By forcing and stimulating TSMC and Samsung to localize its facilities in the USA, American elites tried to solve set of different tasks. Among them were supporting strategic technological autonomy from Asia, and limiting Chinese potential for development (by requiring non-cooperation with PRC in exchange for subsidies). However, due to economic, regulatory, and competence drawbacks efficiency of this new strategy is questionable. Crisis in the electronic industry since the fall of 2022 makes the situation even more problematic. In the mid-term the strategy may not change the balance of power in microchip manufacturing and architecture of relationship with both Asian economies. This requires further development of American economic diplomacy toward Taiwan, RoK – as well as Japan (a so-called “Chip 4” group). This coincides with changes in market dynamics of semiconductor industry. On one hand, geopolitics and value chain resilience became organic factors defining investments and operational expenses. On the other, we may envision sharp rise of competition among nations and companies. Thus, for the long-term success may be determined only by S&T and Innovations (also through industry restructuring) where USA are still strong, but their success isn’t guaranteed anymore.

A Workload and Machine Categorization-Based Resource Allocation Framework for Load Balancing and Balanced Resource Utilization in the Cloud

This paper proposes a workload and machine categorization based resource allocation framework for balancing the load across active physical machines as well as utilizing their different resource capacities in a balanced manner. The workload, essentially independent and non-preemptive tasks are allocated resources on the physical machines whose resource availability complements the resource requirement of tasks. Simulation based experiments are performed using CloudSim simulator to execute three different set of tasks comprising 10000, 20000, and 30000 number of tasks. The metric of load imbalance across active physical machines and the metric of utilization imbalance among their considered resource capacities (i.e., CPU and RAM) are measured in different scheduling cycles of a simulation run. Simulation results show that the proposed resource allocation method outperforms the compared methods in terms of balancing the load across active physical machines and utilizing their different resource capacities in a balanced manner.

Model-dependent task assignment in multi-manned mixed-model assembly lines with walking workers

Due to mass customization and extensive market changes, manufacturing companies seek to enhance the flexibility and reconfigurablility of their assembly lines. For instance, to adjust and adapt the line’s capacity to different products and production requirements, workers may move along the stations, or the tasks may be re-assigned. This paper studies the impact of model-dependent task assignment, workforce reconfiguration, and equipment duplication in mixed-model assembly lines. The studied line is paced, and it can process different product models with different sets of tasks and precedence relations. Task and worker assignments to stations may change in each takt, and the goal is to design a line able to handle a predefined set of situations corresponding to different flows of products entering the line. The paper provides a new Mixed Integer Linear Programming (MILP) formulation to minimize the workforce and equipment costs in mixed-model assembly lines with model-dependent task assignment. We provide an efficient reformulation of the MILP by relying on the dualization approach commonly used in robust optimization. In addition, we employ a constructive matheuristic (CM) and a fix-and-optimize heuristic (FOH) to deal with large-scale instances. Extensive computational experiments performed with well-known benchmarks from the literature show that the suggested approaches perform well in terms of solution quality and computational time. In addition, the results reveal that model-dependent task assignment reduces significantly the equipment cost and the number of workers when compared to the classical mixed-model assembly lines with fixed task assignment and walking workers.

An Energy-Aware Task Scheduling for Quality-of-Service Assurance in Constellations of Nanosatellites.

When managing a constellation of nanosatellites, one may leverage this structure to improve the mission’s quality-of-service (QoS) by optimally distributing the tasks during an orbit. In this sense, this research proposes an offline energy-aware task scheduling problem formulation regarding the specifics of constellations, by considering whether the tasks are individual, collective, or stimulated to be redundant. By providing such an optimization framework, the idea of estimating an offline task schedule can serve as a baseline for the constellation design phase. For example, given a particular orbit, from the simulation of an irradiance model, the engineer can estimate how the mission value is affected by the inclusion or exclusion of individuals objects. The proposed model, given in the form of a multi-objective mixed-integer linear programming model, is illustrated in this work for several illustrative scenarios considering different sets of tasks and constellations. We also perform an analysis of the Pareto-optimal frontier of the problem, identifying the feasible trade-off points between constellation and individual tasks. This information can be useful to the decision-maker (mission operator) when planning the behavior in orbit.

A Lagrangian heuristics for balancing the average weighted completion times of two classes of jobs in a single-machine scheduling problem

• We introduce a new single-machine scheduling problem involving two classes of jobs. • The objective is to balance the average weighted completion times. • We show the NP-hardness of the problem. • We solve the problem by a Lagrangian relaxation heuristics. • Numerical results are presented on a set of randomly generated test problems. We tackle a new single-machine scheduling problem, whose objective is to balance the average weighted completion times of two classes of jobs. Because both the job sets contribute to the same objective function, this problem can be interpreted as a cooperative two-agent scheduling problem, in contraposition to the standard multiagent problems, which are of the competitive type since each class of job is involved only in optimizing its agent's criterion. Balancing the completion times of different sets of tasks finds application in many fields, such as in logistics for balancing the delivery times, in manufacturing for balancing the assembly lines and in services for balancing the waiting times of groups of people. To solve the problem, for which we show the NP-hardness, a Lagrangian heuristic algorithm is proposed. In particular, starting from a nonsmooth variant of the quadratic assignment problem, our approach is based on the Lagrangian relaxation of a linearized model and reduces to solve a finite sequence of successive linear assignment problems. Numerical results are presented on a set of randomly generated test problems, showing the efficiency of the proposed technique.

Designing Online Educational Russian Language Courses in Finland

When switching to online teaching, the question arises about the feasibility, methods and form of transposing existing teaching materials into the Internet and creating new ones. The aim of the study is to show what opportunities electronic educational environment ViLLE, developed in Finland, has for teaching Russian as a foreign language and as a second home language. The material of the article include exercises created in this e-environment, and the methods of the research include various software and pedagogical solutions aimed at implementing the methodology. During research, starting in 2017, e-learning platform ViLLE has allowed the Russian language to find and to take its place in Finlands digital language teaching system. Different courses were created, with different sets of tasks and exercises that can be used by teachers and students of any educational institution. Some of the courses, among them those aimed at bilinguals, provide an opportunity to familiarize students with the included theoretical material. Having mastered the necessary minimum skills of using ViLLE, any teacher can independently modify tasks and exercises, combine them in the desired sequence and volume, and thus create courses adapted to the needs of their students. An integrated performance analysis system makes their work easier by allowing the teacher to focus on a specific language teaching problem. The results showed that among the existing electronic educational resources, online platforms and e-learning environments are the most essential tools for teaching a foreign/second language, since only they give the teacher the opportunity to independently plan and structure the entire educational process, manage it, use existing materials and create new ones, automatize certain functions, combine various educational events, and communicate with students. The article compares criteria for evaluating such resources and dividing them into two categories: (1) general criteria that include multi-functionality, the set of features provided by the environment, and compatibility with regard to encoding and format of training materials and other system components; (2) those considering needs of specific teachers and students and their resources, namely, resource administrating, creating tasks and courses, managing and monitoring the learning process. The future plans concern carrying out extensive monitoring of the effectiveness of the system in school and university teaching.

Future-relevant memories are not selectively strengthened during sleep.

Overnight consolidation processes are thought to operate in a selective manner, such that important (i.e. future-relevant) memories are strengthened ahead of irrelevant information. Using an online protocol, we sought to replicate the seminal finding that the memory benefits of sleep are enhanced when people expect a future test [Wilhelm et al., 2011]. Participants memorised verbal paired associates to a criterion of 60 percent (Experiment 1) or 40 percent correct (Experiment 2) before a 12-hour delay containing overnight sleep (sleep group) or daytime wakefulness (wake group). Critically, half of the participants were informed that they would be tested again the following day, whereas the other half were told that they would carry out a different set of tasks. We observed a robust memory benefit of overnight consolidation, with the sleep group outperforming the wake group in both experiments. However, knowledge of an upcoming test had no impact on sleep-associated consolidation in either experiment, suggesting that overnight memory processes were not enhanced for future-relevant information. These findings, together with other failed replication attempts, show that sleep does not provide selective support to memories that are deemed relevant for the future.

Deep Learning Architectures for Skateboarder–Pedestrian Surrogate Safety Measures

Skateboarding as a method of transportation has become prevalent, which has increased the occurrence and likelihood of pedestrian–skateboarder collisions and near-collision scenarios in shared-use roadway areas. Collisions between pedestrians and skateboarders can result in significant injury. New approaches are needed to evaluate shared-use areas prone to hazardous pedestrian–skateboarder interactions, and perform real-time, in situ (e.g., on-device) predictions of pedestrian–skateboarder collisions as road conditions vary due to changes in land usage and construction. A mechanism called the Surrogate Safety Measures for skateboarder–pedestrian interaction can be computed to evaluate high-risk conditions on roads and sidewalks using deep learning object detection models. In this paper, we present the first ever skateboarder–pedestrian safety study leveraging deep learning architectures. We view and analyze state of the art deep learning architectures, namely the Faster R-CNN and two variants of the Single Shot Multi-box Detector (SSD) model to select the correct model that best suits two different tasks: automated calculation of Post Encroachment Time (PET) and finding hazardous conflict zones in real-time. We also contribute a new annotated data set that contains skateboarder–pedestrian interactions that has been collected for this study. Both our selected models can detect and classify pedestrians and skateboarders correctly and efficiently. However, due to differences in their architectures and based on the advantages and disadvantages of each model, both models were individually used to perform two different set of tasks. Due to improved accuracy, the Faster R-CNN model was used to automate the calculation of post encroachment time, whereas to determine hazardous regions in real-time, due to its extremely fast inference rate, the Single Shot Multibox MobileNet V1 model was used. An outcome of this work is a model that can be deployed on low-cost, small-footprint mobile and IoT devices at traffic intersections with existing cameras to perform on-device inferencing for in situ Surrogate Safety Measurement (SSM), such as Time-To-Collision (TTC) and Post Encroachment Time (PET). SSM values that exceed a hazard threshold can be published to an Message Queuing Telemetry Transport (MQTT) broker, where messages are received by an intersection traffic signal controller for real-time signal adjustment, thus contributing to state-of-the-art vehicle and pedestrian safety at hazard-prone intersections.

Multi-AUV Collaborative Data Collection Algorithm Based on Q-Learning in Underwater Acoustic Sensor Networks

Intelligent data collection is a key component in underwater acoustic sensor networks, and it plays an important role in seabed environment monitoring, marine resource detection and marine disaster early warning. Owing to the particularities of the underwater environment, such as reduced infrastructure and noisy communication channels, the data collected by underwater nodes are more efficiently transmitted to a control center on the surface by way of an autonomous underwater vehicle (AUV). However, with the increasing complexity of the underwater tasks, using a single AUV for data collection cannot meet the requirements of low latency and low power consumption. To solve this problem, a multi-AUV collaborative data collection algorithm that reduces the load of data collection task on a single AUV is proposed. The algorithm is divided into two stages: multi-AUV task allocation and Q-learning-based AUV path planning. The data transmission of the clusters is regarded as a set of different tasks, which are assigned to the AUVs for completion. Subsequently, path planning is performed to guide the AUVs, so that the tasks are completed promptly and at a reduced cost. Simulation results show that the proposed algorithm can leverage the energy consumption of a network and extend its lifetime. The performance of the proposed algorithm in energy consumption is increased by about 10%, and the delay of data collection is also significantly reduced.

Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots.

The paradigm of voxel-based soft robots has allowed to shift the complexity from the control algorithm to the robot morphology itself. The bodies of voxel-based soft robots are extremely versatile and more adaptable than the one of traditional robots, since they consist of many simple components that can be freely assembled. Nonetheless, it is still not clear which are the factors responsible for the adaptability of the morphology, which we define as the ability to cope with tasks requiring different skills. In this work, we propose a task-agnostic approach for automatically designing adaptable soft robotic morphologies in simulation, based on the concept of criticality. Criticality is a property belonging to dynamical systems close to a phase transition between the ordered and the chaotic regime. Our hypotheses are that 1) morphologies can be optimized for exhibiting critical dynamics and 2) robots with those morphologies are not worse, on a set of different tasks, than robots with handcrafted morphologies. We introduce a measure of criticality in the context of voxel-based soft robots which is based on the concept of avalanche analysis, often used to assess criticality in biological and artificial neural networks. We let the robot morphologies evolve toward criticality by measuring how close is their avalanche distribution to a power law distribution. We then validate the impact of this approach on the actual adaptability by measuring the resulting robots performance on three different tasks designed to require different skills. The validation results confirm that criticality is indeed a good indicator for the adaptability of a soft robotic morphology, and therefore a promising approach for guiding the design of more adaptive voxel-based soft robots.

Cluster formation techniques for hierarchical real time tasks allocation on multiprocessor system

SummaryReal‐time systems are nowadays extensively used in most time‐critical embedded applications. The existing multiprocessor real‐time scheduling algorithms are based on partitioned and global scheduling approaches. The partitioned‐based algorithms suffer poor utilization bound, load balancing, not compatible for an open system environment, and the global scheduling approach faces problems like high scheduling, migration overhead. Cluster scheduling represents a hybrid scheduling approach which consists of a set of processors as clusters and tasks scheduled to each processor of clusters using a global scheduling approach. The different cluster formation heuristics are investigated for homogenous clusters. The main objective of this article is to propose task utilization‐based cluster formation and harmonic period aware task allocation for a hierarchical real‐time system on a multiprocessor platform. Tasks with high utilization, cluster size tune to a smaller value to achieve high utilization. Tasks with low utilization, the size of cluster tune to larger to reduce migration and scheduling overheads. Experimentation performed on multiprocessor real‐time simulator with a different set of tasks, multiprocessor system, different tasks utilization, and cluster size. Simulation results show that cluster base approach increases the number of tasks scheduled on a multiprocessor system, system utilization, and reduces response time, migration, and preemption overheads.

The Archaeology of Z: Household Economies in Nineteenth-Century Iceland

A substantial and rapid increase in consumer goods has been detected in the archaeological record from Iceland during the 19th century. This article considers the impact of this change on household routines. Drawing inspiration from economics and Becker’s concept of Z commodities, the analysis seeks to blur the distinction between consumption and production by comparing the demands made on household resources by two different sets of tasks: firstly, those presented by the introduction of new materials related to coffee, and, secondly, those required by the traditional materials of butter production. The article illustrates the ways everyday routines are altered with the introduction of new materials and suggests that the productive work involved in consumption may be a key factor in how people and materials become entangled and mutually dependent.

ACCELERATED AUTOMATION AND THE ECOSYSTEM OF ADAPTATION TO THE CHANGES

The spread of the pandemic has further accelerated the already accelerated process of automation, as it reduces all interactions and helps social distancing, as it was advised to combat the virus. Automation is proceeding at a very fast pace in many sectors of the economy and creating the need for countries to respond to these new challenges at the level of national economic strategy. The new challenge has changed the attitudes of not only manufacturers but also consumers and given them additional impetus to the using robots and artificial intelligence. During this period, those, who are the first to be able to switch to online sales, reduce the need for communication with employees and increase the level of automation, will be able to gain an advantage. Because of this, there is a danger that after the pandemic ends, some of those currently temporarily unemployed will not be able to return to work and will need to adapt to the new reality. In the light of such changes, it is important to identify areas of declining and growing sectors of labor demand and to prepare the population for change to prevent technological unemployment. As it turns out, technological skills and social skills are becoming increasingly demanded, while physical and basic cognitive skills are on the decline. In order to adapt to a new reality, firms have a choice of retraining old employees, redeploying them to different sets of tasks, hiring individuals with skills that are increasingly needed, contracting specialists outside the company (freelancers) and releasing employees that do not fit the new paradigm of business models. Automation involves the disappearance of a large proportion of low-skilled occupations, leading to a critical role for education in employment. It is therefore important for the government to establish a strategic position on higher and professional education, which will be based on a long-term plan for the structural transformation of the workforce. Automation may be used as an opportunity if a productive ecosystem is established and all stakeholders get actively involved in the process of adjusting to the new reality. For that it is necessary to form an overall ecosystem of stakeholders, which should contain employers at the center and different supporting institutions around them. The ecosystem should consist of labor agencies that help individuals find new jobs, retrain and get some benefits. Educational institutions play a crucial role in devising courses and specializations that fit an exact position that is in demand in some companies. Industry associations and non-profit organizations also need to be coordinated with companies to expand this ecosystem. Combined effort of all these five groups of stakeholders can manage to overcome the looming challenge of rapid unemployment growth and wide skill mismatch. If a society fail to coordinate in the ecosystem, the aftermath will be devastating and income inequality will be amplified. One solution to that is thought to be universal basic income (UBI) but so far it doesn’t seem feasible and cannot be relied on. Adapting society to a change instead of giving out basic income seems to address the problem better and not just on a surface.

The method to study the competencies of the subjects of the digital economy

The purpose of the paper is to present the author’s method to study the competencies required to organizations for the digital economy development. The widespread use of mobile computing devices by citizens in their daily and professional activities, the growth of the internet of things, the accumulation of Big Data, the improvement and emergence of new information technologies (IT) open up new opportunities for conducting economic activities, provided that the subjects possess the competencies of the digital economy. Materials and methods . The research is based on the analysis of IT development trends and options for their application in various types of economic activities. The approach of linear programming was used as a basis, which allowed us to present a bunch of competencies in the form of a matrix. The information base of the study was made up of methodological approaches used in economics and science to research digital competencies, as well as data from reports of leading consulting companies. Results. The author’s method has been developed for studying the competences of digital economy subjects as a large set of knowledge and skills for using modern IT to solve current economic problems. The research method consists in structuring the bunch in the form of a matrix, the size of which is determined by the number of modern IT and economic activities. The values in the matrix reflect the number of competencies of the subject to use a specific IT in a particular type of activity. Conclusion. In modern conditions of digitalization of society, digital competencies are represented by a large set of knowledge and skills. The use of one IT in different activities solves a different set of tasks, and competence assumes the ability of the subject to solve a certain problem using it. Many competencies will continue to grow as the digital economy develops. Limiting the bunch of competencies to a list of universal competencies will lead to a rapid loss of its relevance to the economy. The developed method makes it possible to conduct research on the availability of organizations with the necessary competencies, to identify areas where it is necessary to form new competencies or adapt them from other types of economic activity.

TARNN: Task‐aware autonomic resource management using neural networks in cloud environment

SummaryResource management is one of the major issue in cloud computing for IaaS. Among several resource management problems allocation, provisioning, and requirement mapping directly affects the performance of cloud. Resource allocation signifies assignment of available resources to different workloads in an economically optimal manner. Precise and accurate allocation is required to maximize the usage of resources. Current method of task allocation do not take previously acquired knowledge, type of the tasks, and the QoS parameters altogether into account in the allocation phase, and it has not been trained for different set of tasks. Furthermore, the self‐optimization of the autonomous system fails to address the task type and identify the relationship between tasks and the resource demands along with its requirements. Important aspects like task management and resource utilization are the primary factors to consider for such a characteristic. This paper will present a novel autonomic resource management framework named task‐aware autonomic resource allocation strategy using neural networks (TARNN), which aims to use knowledge about the behavior of the task over an extended period of time and use this knowledge to allocate resources when a similar task is submitted in future by the user. To effectively do the allocation, a neural network–based approach is adopted to classify the tasks appropriately based on the task parameters, task type, and QoS parameters and allocate the resource optimally for a new task autonomously, without the intervention of the cloud provider. Moreover, to identify and improve the relationship of the tasks with the resources in the context of scheduling, we have proposed a novel modified Particle Swarm Optimization (m‐PSO) algorithm to schedule the tasks to resources based on resource demands. In TARNN, we have separated the collected synthetic dataset into 60‐40 ratio for training and testing purposes. We found that the neural network–based approach provides almost 80% accurate classification w.r.t. task type and QoS parameters. We have also compared our results with support vector machine (SVM) and got 69% accuracy. Since the tasks are classified appropriately, the occurrence of resource reconfiguration and VM migration is drastically reduced. Hence, our system provides better allocation of resources and schedules the tasks appropriately to the resources, thereby improving the performance of the cloud.

МЕТОДИКА ОБРАБОТКИ ИНФОРМАЦИИ ДЛЯ ОПРЕДЕЛЕНИЯ ОТНОСИТЕЛЬНОГО УРОВНЯ МОРАЛЬНОГО ИЗНОСА ОБОРУДОВАНИЯ ОПЕРАТОРА СВЯЗИ

To decide on the development of network infrastructure, it is necessary to take into account not only the physical state of the equipment, but also the degree of its obsolescence. The analysis of methods for determining obsolescence revealed constraints related to inadequate study of the issues of accounting for the effectiveness of telecommunications equipment, depending on the specifics of operation and the state of the market for the supply of similar technical solutions. To eliminate the identified limitations, a technique for processing information for determining the obsolescence of equipment of telecommunications operators was proposed. The methodology consists in the formation of the ratio of the evaluation of the equipment used by the operator to the integral evaluation of the conditional device, which is formed taking into account the average parameters of similar technical solutions available on the telecommunications equipment market. The article gives an example of practical application of the method: assessment of the condition of the commutators D-Link DGS-3420-28TC and D-Link DES-3200-28/C1A. The advantage of the method is that it takes into account specific features and operational conditions of the equipment, because the equipment is to fulfill different sets of tasks and can be recognized either efficient, or inefficient in different cases. Practical use of the proposed method allows the development of software for analysis and processing information on the management of the development of the infrastructure of networks of telecommunications operators and Internet providers.