Network Management Problems Research Articles

Adaptive network traffic control with approximate dynamic programming based on a non-homogeneous Poisson demand model

ABSTRACT In this study, we develop a stochastic dynamic traffic-flow model subject to practical restrictions under the non-homogeneous Poisson vehicle arrival process. Using the cell transmission strategy, we establish traffic dynamics between two intersections. We also discuss simulating the random demand of source links from an estimated intensity function. Additionally, we propose an algorithm to optimize time interval division for aggregated data, aiming to enhance estimation performance. We explore applying our traffic flow model to the adaptive traffic network management problem, which is formulated as a Markov decision process. Leveraging approximate dynamic programming with recursive least squares-temporal difference learning, we achieve adaptive optimal policies. To validate our approach, we conduct a series of numerical experiments with random demands. The results of non-homogeneous Poisson demand conducted using random numbers and a real-word dataset indicate high efficiency with the piecewise constant, I-SMOOTH, and MNO-PQRS estimators. Compared to the Webster and Max-pressure control systems, our proposed approximate dynamic programming-based model exhibits superior stability and applicability.

Decentralized robust operation of the unbalanced microgrids in distribution networks: A convex relaxation approach

This work presents a distributed robust operation framework for the microgrids within the power distribution network. It addresses the uncertainties in photovoltaic generation, as well as active, and reactive loads in the network, by modeling them using polyhedral sets. The energy management problems are formulated as two-stage optimization problems in microgrids and power distribution networks for which Benders decomposition is used to solve the problems. The power flow constraints are relaxed using second-order cone relaxation and moment relaxation techniques in the power distribution network and microgrid energy management problems, respectively. The interaction between the microgrids and the power distribution network is represented using the price signal and the exchanged active and reactive power at the microgrids’ points of common coupling. The effectiveness of the proposed framework is shown using two case studies on IEEE 37-bus and IEEE 123-bus systems. The effect of the energy storage system on the operational cost of the system is assessed. It is shown that total operation cost is decreased by 9.69% when the energy storage system is integrated into the power distribution network. Additionally, the solution derived from the robust problem is compared with that of the deterministic problem.

Customer segmentation, pricing, and lead time decisions: A stochastic-user-equilibrium perspective

Multiple price/lead time options are often used as a competitive tool in supply chain operations when customers have heterogeneous price and lead time preferences. We study a two-echelon supply chain network consisting of manufacturers and retailers facing customers that differ in their price- and time-sensitivity. We examine how many price/lead time options should be provided by manufacturers and retailers under decentralized and centralized supply chain management with time-cost tradeoffs. We adopt a stochastic-user-equilibrium (SUE) approach in a supply chain network by incorporating discrete choice theory and using a multinomial logit-based variational inequality to express equilibrium conditions. This is one of the first papers to study time-cost tradeoffs in a supply chain network by introducing an SUE approach. One critical part of our analysis is the establishment of concavity of profit functions, which allows for analytical derivation of the equilibrium strategies. Another critical part of our analysis is the development of SUE conditions in decentralized and centralized supply chain networks. We demonstrate that the variance of heterogeneous customers’ time-sensitivity distribution plays a crucial role in customer segmentations in a time-cost tradeoff supply chain. We find that under SUE conditions, there exists a unique equilibrium in the decentralized and centralized supply chain networks, respectively. We conduct comparative statics analyze to demonstrate the effect of SUE and UE conditions and the influence of decentralized versus centralized supply chain management paradigms. We show how the SUE approach can be applied to supply chain network management with time-cost tradeoffs. Our approach can be extended to other tradeoff decision problems in supply chain network management, especially those in which customers are heterogeneous.

Multi-agent deep reinforcement learning based resource management in SWIPT enabled cellular networks with H2H/M2M co-existence

Machine-to-Machine (M2M) communication is crucial in developing Internet of Things (IoT). As it is well known that cellular networks have been considered as the primary infrastructure for M2M communications, there are several key issues to be addressed in order to deploy M2M communications over cellular networks. Notably, the rapid growth of M2M traffic dramatically increases energy consumption, as well as degrades the performance of existing Human-to-Human (H2H) traffic. Sustainable operation technology and resource management are efficacious ways for solving these issues. In this paper, we investigate a resource management problem in cellular networks with H2H/M2M coexistence. First, considering the energy-constrained nature of machine type communication devices (MTCDs), we propose a novel network model enabled by simultaneous wireless information and power transfer (SWIPT), which empowers MTCDs with the ability to simultaneously perform energy harvesting (EH) and information decoding. Given the diverse characteristics of IoT devices, we subdivide MTCDs into critical and tolerable types, further formulating the resource management problem as an energy efficiency (EE) maximization problem under divers Quality-of-Service (QoS) constraints. Then, we develop a multi-agent deep reinforcement learning (DRL) based scheme to solve this problem. It provides optimal spectrum, transmit power and power splitting (PS) ratio allocation policies, along with efficient model training under designed behavior-tracking based state space and common reward function. Finally, we verify that with a reasonable training mechanism, multiple M2M agents successfully work cooperatively in a distributed way, resulting in network performance that outperforms other intelligence approaches in terms of convergence speed and meeting the EE and QoS requirements.

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification

Realizing human-like perception is a challenge in open driving scenarios due to corner cases and visual occlusions. To gather knowledge of rare and occluded instances, federated learning assisted connected autonomous vehicle (FLCAV) has been proposed, which leverages vehicular networks to establish federated deep neural networks (DNNs) from distributed data captured by vehicles and road sensors. Without the need of data aggregation, FLCAV preserves privacy while reducing communication costs compared with conventional centralized learning. However, it is challenging to determine the network resources and road sensor placements for multi-stage training with multi-modal datasets in multi-variant scenarios. This article presents networking and training frameworks for FLCAV perception. Multi-layer graph resource allocation and vehicle-road contrastive sensor placement are proposed to address the network management and sensor deployment problems, respectively. We also develop CarlaFLCAV, a software platform that implements the above system and methods. Experimental results confirm the superiority of the proposed techniques compared with various benchmarks.

Research on supply chain risk evaluation based on clustering method

This paper presents a supply chain risk evaluation and prediction model based on K-means clustering and LightGBM classifier. Supply chain risk evaluation and prediction is an important problem. With the development of economic globalization, market competition is not the competition between enterprises as in the past, but the competition between supply chains. The model takes many variables such as market environment factors, resource constraints, transportation network factors and management factors as inputs. The data we used is a supply chain data set of an equipment group, which covers many variables such as market environment factors, resource constraints, transportation network factors and management factors. After the supply chain risk evaluation based on K-means clustering, the model is classified by LightGBM to generate the prediction model, and the effectiveness of the model is verified on the real data set. The results of K-Means cluster evaluation show that supply chain risk can be divided into four categories: market environment problems, resource constraints, transportation network problems and management problems, among which market environment problems and resource constraints are the most frequent.

The Cultivation of Political Identity Literacy in Ideological and Political Classroom Based on IOT and Knowledge Map

The learning depth and training temperature of citizen research course are realized through preclass preview and exploration of life situation and strengthen emotional noncognitive learning by guiding students through preschool preview, life situation exploration, hot topic dialogue and questions, experience transfer and application, and creating practical activities. In order to achieve the purpose of critical understanding and real problem-solving, I integrated and refined the learning content, from emotion to internal political identity and realized the organic combination of in-depth learning and classroom training. Combined with the development of Multimedia Internet of Things in the classroom, a new software is developed to solve the problem of multimedia network management that connects to other central media control devices and auxiliary devices through the Internet of Things. This paper introduces the design idea and overall structure of the system and discusses the changes brought by the network structure to the multimedia network. The network architecture of multimedia classroom based on SDN and Internet of Things helps to solve the practical problems in the use of existing multimedia classroom, improve the intelligence of multimedia classroom, and better serve teachers and students.

Investigation of the Bayesian and non-Bayesian time series forecasting frameworks in application to OSS systems of the LTE/LTE-A and 5G mobile networks

Applicability of some conventional Time-Series prediction models for the temporal dynamics of the EPS Radio Bearer Setup Failure Rate is examinated in this paper. Two main problems of the proactive network management have been considered: the prediction of regular part of time series and the outliers prediction. For the regular part prediction Holt-Winters Exponential Smoothing, Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Python Dynamic Linear Model (PyDLM) and Seasonal Auto Regressive Integrated Moving Average (SARIMAX) have been used. The error performance has been analyzed using Median Absolute Error, Mean Absolute Error, Mean Square Error and Root Mean Square Error. A two-step approach has been proposed for the outliers prediction. Deployment of such approach is justified by the fact, which the time moments of the anomalies, are preferable for practical purposes. On the first step, the values of time-series are predicted using one of the above mentioned models. On the second step the resulting values from the step one are classified using discrete state Hidden Markov Model. For the error performance estimation purpose True Positive, False Positive and False negative rates have been calculated for the respective models. Finally, several proposals for the usage of the considered algorithms in a proactive offline network management in Operation Support System (OSS) or Network Data Analytics Function (NWDAF) have been made.

Design Specification for Network Fault Diagnosis System

As the network becomes more and more complex and heterogeneous, the problem of network management becomes more and more prominent. The research and application of network management is of great significance for ensuring the normal operation of network and improving the reliability and availability of network system. The main problems of network management are network configuration, failure, performance, security, planning and scaling, etc. On the basis of in-depth research and discussion on network management and fault management, this paper designs the system requirements of network fault diagnosis system.

Guest Editorial: Interplay between Machine Learning and Networking Systems

Recently, the advancement of machine learning (ML) techniques, especially deep learning, reinforcement learning, and federated learning, has led to remarkable breakthroughs in a variety of application domains. The success of ML benefits from the advancement of the Internet, mobile networks, data center networks, and the Internet of Things (IoT) that facilitate data creation and sharing. On the other hand, we have also witnessed a fast growing trend in the networking community toward using ML to tackle challenging problems in network design, management, and optimization, which are traditionally addressed using mathematical optimization theory or human-generated heuristics. ML is also an essential ingredient in the realization of autonomous or self-driving networks.

Graph neural network‐based virtual network function deployment optimization

SummarySoftware‐defined networking (SDN) and network function virtualization (NFV) help reduce the operating expenditure (OPEX) and capital expenditure (CAPEX) as well as increase the network flexibility and agility. However, since the network is more dynamic and heterogeneous than before, operators have problems to cope with the increased complexity of managing virtual networks and machines. This complexity is paired with strict time requirements for making management decisions; traditional mechanisms that rely on, for example, integer linear programming (ILP) models are no longer feasible. Machine learning has emerged as one of the possible solution to address network management problems to get near‐optimal solutions in a short time. However, applying machine learning to network management is also not simple and has many challenges. Especially, understanding the network environment is an important problem for designing a machine learning model. In this paper, we proposed to use graph neural network (GNN) for virtual network function (VNF) management. The proposed model solves the complex VNF management problem in a short time and gets near‐optimal solutions. We developed a model by taking into account various network environment conditions so that it can be applied in the actual network environment. Also, through in‐depth experiments, we suggested the direction of the machine learning‐based network management method.

Solving Bi-objective Model of Hotel Revenue Management Considering Customer Choice Behavior Using Meta-heuristic Algorithms

The problem of maximizing the benefit from a specified number of a particular product with respect to the behavior of customer choices is regarded as revenue management. This managerial technique was first adopted by the airline industries before being widely used by many others such as hotel industries. The scope of this research is mainly focused on hotel revenue management, regarding which a bi-objective model is proposed. The suggested method aims at increasing the revenue of hotels by assigning the same rooms to different customers. Maximization of hotel revenue is a network management problem aiming to manage several resources simultaneously. Accordingly, a model is proposed in this paper based on the customer choice behavior in which the customers are divided into two groups of business and leisure. Customers of the business group prefer products with full price, whereas products with discounts are most desirable for leisure customers. The model consists of two objectives, the first one of which maximizes the means of revenue, and the second one minimizes the dispersion of revenue. Since the problem under consideration is Non-deterministic Polynomial-time hard (NP-hard), two meta-heuristic algorithms of Non-dominated Sorting Genetic Algorithm-II (NSGA-II) and Multiple Objective Particle Swarm Optimization (MOPSO) are proposed to solve the problem. Moreover, the tuned algorithms are compared via the statistical analysis method. The results show that the NSGA-II is more efficient in comparison with MOPSO.

Application of Computer Network Communication Technology in Production and Life

China’s rapid economic development, while the level of science and technology has also made great progress, communication engineering is the national infrastructure, in the process of development, we should pay more attention to network security. In the application of computer network communication security technology, the application of data encryption technology is to ensure people’s privacy and security. Today, with the rapid development of Internet technology, computers have been integrated into our life. No matter in study or work, computers are always with us. At present, there are still great risks in the process of using the computer, so data encryption is essential to ensure the security of information and users when the computer is running. The security of computer data and information has gradually become a very important part of computer network management. this paper makes a preliminary analysis and discussion on the problems of computer network management and information security prevention.

Systematic Beam Management in mmWave Networks: Tradeoff Among Beam Coverage, Link Budget, and Interference Control

In this paper, we study the beam management problem in mmWave networks from a systematic perspective. Instead of maximizing the network performance in terms of user sum-rate, we improve the beam coverage, which could potentially reduce beam tracking overhead for mobile users. Moreover, to compensate the severe signal attenuation in mmWave bands, we configure the beam to meet the user link budget requirement. To reduce the interference among users, we take the inter-beam interference from both main-lobe and side-lobe into consideration. Overall, we formulate our beam management scheme as a non-linear integer optimization problem. By deliberately transforming it to a geometric optimization problem and designing a rounding method, we develop a suboptimal solution, with low computational complexity. Based on this, we further design a scheduling user set refining method, which can assist user scheduling in the MAC layer, to make the beam configuration request within the antenna capability. Extensive simulation results demonstrate that our proposed algorithm could manage the beam on-line, while satisfying beam configuration requests for beam coverage, link budget, and inter-beam interference control.

A Reinforcement Learning-Based Network Traffic Prediction Mechanism in Intelligent Internet of Things

Intelligent Internet of Things (IIoT) is comprised of various wireless and wired networks for industrial applications, which makes it complex and heterogeneous.The openness of IIoT has led to the intractable problems of network security and management. Many network security and management functions rely on network traffic prediction techniques, such as anomaly detection and predictive network planning. Predicting IIoT network traffic is significantly difficult because its frequently updated topology and diversified services lead to irregular network traffic fluctuations. Motivated by these observations, we proposed a reinforcement learning-based mechanism in this article. We modeled the network traffic prediction problem as a Markov decision process, and then, predicted network traffic by Monte Carlo $Q$ -learning. Furthermore, we addressed the real-time requirement of the proposed mechanism and we proposed a residual-based dictionary learning algorithm to improve the complexity of Monte Carlo $Q$ -learning. Finally, the effectiveness of our mechanism was evaluated using the real network traffic.

Learn to Schedule (LEASCH): A Deep Reinforcement Learning Approach for Radio Resource Scheduling in the 5G MAC Layer

Network management tools are usually inherited from one generation to another. This was successful since these tools have been kept in check and updated regularly to fit new networking goals and service requirements. Unfortunately, new networking services will render this approach obsolete and handcrafting new tools or upgrading the current ones may lead to complicated systems that will be extremely difficult to maintain and improve. Fortunately, recent advances in AI have provided new promising tools that can help solving many network management problems. Following this interesting trend, the current article presents LEASCH, a deep reinforcement learning model able to solve the radio resource scheduling problem in the MAC layer of 5G networks. LEASCH is developed and trained in a sand-box and then deployed in a 5G network. The experimental results validate the effectiveness of LEASCH compared to conventional baseline methods in many key performance indicators.

Incorporating cost uncertainty and path dependence into treatment selection for pavement networks

This paper proposes a new probabilistic treatment path dependence (PTPD) model for budget allocation within pavement network management problems. During the evaluation of treatment alternatives for a segment in a pavement network, the model considers benefits of both the evaluated treatment and its following actions. It also incorporates the influence of treatment cost and deterioration uncertainties. Treatments are selected for each segment in the pavement network using a risk-based optimization model. Three case studies are presented to illustrate the application and benefits of this new model. Results of the first two cases show that the risk-aversion coefficient in the model influences segment-level treatment selections and pavement network performance. The third case shows that the PTPD model performs better than a benefit-cost ratio model due to the incorporation of uncertainties and treatment path dependence. To obtain a similar performance level, the conventional model requires a 10.4% higher annual budget for the given case study. The results presented here suggest that elements of this model – notably consideration of uncertainty in deterioration and cost, treatment path dependency, and explicit risk trade-offs – could be incorporated into asset management tools to improve the cost-effectiveness of pavement network planning.

An integer programming formulation of the key management problem in wireless sensor networks

With the advent of modern communications systems, much attention has been put on developing methods for securely transferring information between constituents of wireless sensor networks. To this effect, we introduce a mathematical programming formulation for the key management problem, which broadly serves as a mechanism for encrypting communications. In particular, an integer programming model of the q-Composite scheme is proposed and utilized to distribute keys among nodes of a network whose topology is known. Numerical experiments demonstrating the effectiveness of the proposed model are conducted using using a well-known optimization solver package. An illustrative example depicting an optimal encryption for a small-scale network is also presented.

Analysis of the peculiarity the main concepts of construction virtual networks

The TCP / IP stack-based communication environment does not always meet the needs of the speed of commissioning and the speed of reconfiguration of modern multiservice networks. The solution to this problem is to implement such a network architecture, in which the logic of traffic management is removed from the software of routers and switches and designed as a separate logic of centralized network management. A network built on this architecture is called Software Defined Network (SDN). Logically centralized software model does not mean physical centralization of the system. Instead, SDN workstations rely on physically distributed control levels. Sharing these levels is key to achieving the desired flexibility of the network, while separating the problem of network management into simpler tasks while simplifying the introduction of new abstractions. The article covers the concept of software-configured networks in the context of two concepts of their construction, namely, software-defined (SDN) networks and virtualization of network functions (NVF). The NVF approach involves separating the functions of logical network elements from their hardware infrastructure by virtualizing such functions. All of this makes it possible to use unified computer hardware that delivers extensive computing capabilities to manage bandwidth. In this case, the resources of the unified equipment can be dynamically redistributed between the software implemented virtual network functions. In terms of practical implementation, the NVF concept is more interesting now. In this model, the switches do not abstract from the performance of network management functions, but only delegate such functions to the SDN controller or to some set of virtual network services. Despite the later appearance of telecommunication services, compared to the concept of SDN, telecommunications market operators are considering the possibility of implementing NVF solutions in the short and medium term. The main reasons for this are, firstly, that the implementation of NVF can be limited and progressive through the provision of new services and without early replacement of successfully used equipment. Second, for MVF solutions, unlike SDN solutions, there is already a well-established application practice associated with cloud and other solutions that makes the NVF concept more mature and commercially available. The main factors hampering the development of NFVs include insufficiently developed standards, leading to diversity in vendor implementations and NFV interoperability issues across vendors; organizational problems of telecommunication operators are connected with necessity of transfer of a part of functions from technical department to the department of information technology. In general, the transition to NFV can be compared to the transition from analogue telephone exchanges to digital ones in the early 1970s, when equipment manufacturers experienced the same reorientation and re-equipment.

Network Management of Multicluster RT-WiFi Networks

Applying wireless technologies in cyber-physical systems (CPSs) has received significant attention in recent years. In our previous work, a high-speed and flexible real-time wireless communication protocol called RT-WiFi was designed to support a wide range of CPSs, and we presented an implementation with a single access point (AP). To serve the CPS applications with communication nodes geographically distributed over a large area, multicluster RT-WiFi networks with multiple APs need to be deployed. Although effective scheduling algorithms have been designed to schedule tasks in RT-WiFi networks with a single AP, uncoordinated packet transmissions from multicluster RT-WiFi networks may suffer from cochannel interferences that cause performance degradation. The multicluster RT-WiFi network management problem is to resolve the cochannel interference through channel assignment for clusters and through phasing assignment for communication tasks. In this article, we first derive a conjunctive normal form encoding of the problem and design a TScheduler that searches feasible solutions through the SAT solver. A novel LRTree Scheduler is further designed to solve the problem in chain graphs while keeping the number of used channels small and the network management overhead low. A testbed of the multicluster RT-WiFi network is deployed to validate the design of the multicluster RT-WiFi network and evaluate the performance of the proposed scheduling algorithms compared to the contention-based methods in regular WiFi networks. Performance of these scheduling algorithms in large-scale networks is further evaluated through extensive simulations on both static and dynamic multicluster RT-WiFi networks.