Showing papers on "Network management published in 2022"

A Graph Neural Network-Based Digital Twin for Network Slicing Management

Abstract: Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.

A Graph Neural Network-Based Digital Twin for Network Slicing Management

Abstract: Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.

Deep Reinforcement Learning for Resource Management on Network Slicing: A Survey

Abstract: Network Slicing and Deep Reinforcement Learning (DRL) are vital enablers for achieving 5G and 6G networks. A 5G/6G network can comprise various network slices from unique or multiple tenants. Network providers need to perform intelligent and efficient resource management to offer slices that meet the quality of service and quality of experience requirements of 5G/6G use cases. Resource management is far from being a straightforward task. This task demands complex and dynamic mechanisms to control admission and allocate, schedule, and orchestrate resources. Intelligent and effective resource management needs to predict the services’ demand coming from tenants (each tenant with multiple network slice requests) and achieve autonomous behavior of slices. This paper identifies the relevant phases for resource management in network slicing and analyzes approaches using reinforcement learning (RL) and DRL algorithms for realizing each phase autonomously. We analyze the approaches according to the optimization objective, the network focus (core, radio access, edge, and end-to-end network), the space of states, the space of actions, the algorithms, the structure of deep neural networks, the exploration–exploitation method, and the use cases (or vertical applications). We also provide research directions related to RL/DRL-based network slice resource management.

A Flow-Based Anomaly Detection Approach With Feature Selection Method Against DDoS Attacks in SDNs

Abstract: Software Defined Networking (SDN) is an emerging network platform, which facilitates centralised network management. The SDN enables the network operators to manage the overall network consistently and holistically, regardless the complexity of infrastructure devices. The promising features of the SDN enhance network security and facilitate the implementation of threat detection systems through software applications using open APIs. However, the emerging technology creates new security concerns and new threats that do not exist in the current traditional networks. Distributed Denial of Service attacks (DDoS) are one of the most rampant attacks that can interrupt the functionality of the network and make most of the network services unreachable for network users. The efficient identification of DDos attacks on SDN environments in literature is still a challenge because of the number of network features taken into account and the overhead of applying machine learning based anomaly detection techniques. Hence, in this paper, we aim to use two popular feature selection methods, i.e., Information Gain (IG) and Random Forest (RF) in order to analyse the most comprehensive relevant features of DDoS attacks in SDN networks. Using the most relevant features will improve the accuracy of the anomaly detection system and reduce the false alarm rates. Moreover, we propose a Deep Learning (DL) technique based on Long Short Term Memory (LSTM) and Autoencoder to tackle the problem of DDoS attacks in SDNs. We perform our analysis and evaluation on three different datasets, i.e., InSDN, CICIDS2017 and CICIDS2018. We also measure the overhead of the proposed DL model on the SDN controller and test the network performance in terms of network throughput and end-to-end latency. The results validate that the DL approach can efficiently identify DDoS attacks in SDN environments without any significant degradation in the controller performance.

Software-Defined Networking: Categories, Analysis, and Future Directions

Abstract: Software-defined networking (SDN) is an innovative network architecture that splits the control and management planes from the data plane. It helps in simplifying network manageability and programmability, along with several other benefits. Due to the programmability features, SDN is gaining popularity in both academia and industry. However, this emerging paradigm has been facing diverse kinds of challenges during the SDN implementation process and with respect to adoption of existing technologies. This paper evaluates several existing approaches in SDN and compares and analyzes the findings. The paper is organized into seven categories, namely network testing and verification, flow rule installation mechanisms, network security and management issues related to SDN implementation, memory management studies, SDN simulators and emulators, SDN programming languages, and SDN controller platforms. Each category has significance in the implementation of SDN networks. During the implementation process, network testing and verification is very important to avoid packet violations and network inefficiencies. Similarly, consistent flow rule installation, especially in the case of policy change at the controller, needs to be carefully implemented. Effective network security and memory management, at both the network control and data planes, play a vital role in SDN. Furthermore, SDN simulation tools, controller platforms, and programming languages help academia and industry to implement and test their developed network applications. We also compare the existing SDN studies in detail in terms of classification and discuss their benefits and limitations. Finally, future research guidelines are provided, and the paper is concluded.

Analysis of Network Slicing for Management of 5G Networks Using Machine Learning Techniques

Abstract: Consumer expectations and demands for quality of service (QoS) from network service providers have risen as a result of the proliferation of devices, applications, and services. An exceptional study is being conducted by network design and optimization experts. But despite this, the constantly changing network environment continues to provide new issues that today’s networks must be dealt with effectively. Increased capacity and coverage are achieved by joining existing networks. Mobility management, according to the researchers, is now being investigated in order to make the previous paradigm more flexible, user-centered, and service-centric. Additionally, 5G networks provide higher availability, extremely high capacity, increased stability, and improved connection, in addition to quicker speeds and less latency. In addition to being able to fulfil stringent application requirements, the network infrastructure must be more dynamic and adaptive than ever before. Network slicing may be able to meet the present stringent application requirements for network design, if done correctly. The current study makes use of sophisticated fuzzy logic to create algorithms for mobility and traffic management that are as flexible as possible while yet maintaining high performance. Ultimately, the purpose of this research is to improve the quality of service provided by current mobility management systems while also optimizing the use of available network resources. Building SDN (Software-Defined Networking) and NFV (Network Function Virtualization) technologies is essential. Network slicing is an architectural framework for 5G networks that is intended to accommodate a variety of different networks. In order to fully meet the needs of various use cases on the network, network slicing is becoming more important due to the increasing demand for data rates, bandwidth capacity, and low latency.

A Systematic Review of Empirical Emergency Management Network Research: Formation and Development, Properties, and Performance

Abstract: Although network analysis has gained much attention in emergency management studies, there are few systematic reviews of emergency management network studies in public administration. After reviewing 44 journals, this article identified and reviewed a total of 58 studies that conducted network analysis in the context of emergency management. Based on existing literature, this article summarizes the common and unique factors driving network formation and development, describes the structural characteristics of emergency management networks, and reports the performance measures that have been used to evaluate network performance. It concludes by addressing research gaps, presenting propositions and recommendations for future research, and highlighting implications for emergency management practice. The context of this review is emergency management, but the three network research streams focused upon—network formation and development, network properties, and network performance—are relevant to all management and policy domains. This review also underscores the need to further explore the dynamic process of network formation and outcomes of network relationships and structures.

New Sensor Nodes, Cloud, and Data Analytics: Case Studies on Large Scale SHM Systems

Abstract: The progress in the world of new sensors is running fast, offering good performances, and reliable solutions with initial costs orders of magnitude lower than those faced only a few years ago. The spread of new electronic devices, like microcontrollers, the increasing power of the networks for data transmission and management and in the end the availability of the new data-driven approaches have created a revolution in SHM approaches, not yet fully mastered. The way to design a SHM system is going to be deeply revised in an industrial perspective, within a complex framework in which everything has to be planned into details since the beginning, including the development of a metrological culture, the personnel education, the need of spare parts, re-calibration, …. This also means a revolution in data management: huge data flows not only create hardware problems related to their transfer; the software too requires a great deal of effort to compress data, also due to the actual cost of cloud resources. All these facts, accounting for the real metrological performances of the best MEMS sensors available at present, also require simplified data analyses, as software complexity is now mainly transferred to the network management. A trade-off must be looked for between the big redundancy offered by the actual networks and the need of a simple and prompt information, granting the structure safety: That is why as the data rates increase, the algorithms to be adopted must be simple, reliable, eventually adapted to edge computing at the sensor level, where hardware power is now present though at a reduced scale. The chapter shows such an approach in a real case from the system design, its birth, and its proper use for damage detection, up to the detection of a structural failure.

Dynamic Radio Access Selection and Slice Allocation for Differentiated Traffic Management on Future Mobile Networks

Abstract: The development of future wireless networks focuses on providing services with strict, dynamic, and diverse quality of service (QoS) requirements. In this sense, the network slicing paradigm arises as a critical piece on the efficient allocation and management of network resources, allowing for dividing the network into several logical networks with specific functionalities and performance. This paper aims at finding the best combination of access network and network slices over a heterogeneous environment to fulfill users’ requests and optimize network resources usage. We propose the Dynamic radio Access selection and Slice Allocation (DASA) algorithm, flexibly adapted to network conditions, user priorities, and mobility behavior. DASA is based on a multi-attribute decision making (MADM) and analytical hierarchy process (AHP) to face the complex problem of network selection. Moreover, it uses a cooperative game theory approach to handle load balancing during overload situations. This work presents an integral solution that combines software-defined network (SDN) and network function virtualization (NFV) technologies to improve network performance and user satisfaction. DASA algorithm is evaluated through network-level simulations, focusing on flexibility and the effective utilization of network resources during network selection and load balancing mechanisms.

Private management of public networks? Unpacking the relationship between network management strategies in infrastructure implementation

Abstract: With the aim to successfully implement infrastructure, implementation arrangements increasingly assign responsibilities for network management to private actors. In the literature, two types of network management strategies are distinguished: process design and institutional design. To date, research has focused on either of these strategies. Moreover, while private actors aim to use the institutional capital built in the network before the private actor was introduced, the role of institutional capital in network management is often overlooked. Taking these research gaps together, we aim to explore the relationship between the two network management strategies and the intermediating role of institutional capital. We compare three cases of infrastructure implementation from the Netherlands. We find that institutional design strategies, through setting the network rules in the implementation arrangement, can ignite a virtuous or a vicious circle, respectively, hindering or enhancing opportunities for network management through process design.

Network Temperature: A Novel Statistical Index for Networks Measurement and Management

Abstract: Being able to monitor each packet path is critical for effective measurement and management of networks. However, such detailed monitoring can be very expensive especially for large-scale networks. To address such problem, inspired by thermodynamics, which uses the statistical characteristics of a large number of molecules’ motion but not each molecule’s trajectory for analysis, we propose the new concept of network temperature together with the notions of network-specific heat and network temperature gradient. Our approach does not only provide a statistical view of the current network state consisting of all the active packet paths at each time instant, but can be used to represent transitions among network states. Our network temperature-based methods have a broad applicability, such as to DDoS detection, dynamic node importance ranking, network stability and robustness evaluation, reliable packets routing, provenance compression assessment, and so on. Numerical and/or the experimental results show that our methods are effective.

Satellite-Terrestrial Integrated 6G: An Ultra-Dense LEO Networking Management Architecture

Abstract: With the rapid development of low earth orbit (LEO) satellites, the ultra-dense LEO satellite-terrestrial integrated networking has become a promising paradigm to provide wide coverage, high capacity and flexible services for the sixth generation (6G) mobile communication networks. However, the natural heterogeneity, high dynamics, and large scale of ultradense LEO satellite networks pose new challenges to network control and management. To this end, in this article, we propose a medium earth orbit (MEO), low earth orbit (LEO) and satellite Earth stations (SESs) integrated multi-layered management architecture for the ultra-dense LEO satellite network, where global controllers and local controllers are introduced to reduce the network management complexity. With the aid of this hybrid multi-layered management framework, we can efficiently implement the network status control, mobility management, resource management, and service management in the satelliteterrestrial integrated network. To obtain proper global and local controllers with high management efficiency in the hybrid multilayered network management architecture, we further propose a novel and efficient grouping and clustering method for the ultradense LEO satellite network, where each group manager MEO satellite and cluster head (CH) LEO satellites are respectively considered as the global and local controllers of each LEO satellite group. Numerical simulations are carried out to evaluate the superiority and effectiveness of the proposed hybrid multilayered ultra-dense LEO networking management architecture.

Guiding large-scale management of invasive species using network metrics

Abstract: Complex socio-environmental interdependencies drive biological invasions, causing damages across large spatial scales. For widespread invasions, targeting of management activities based on optimization approaches may fail due to computational or data constraints. Here, we evaluate an alternative approach that embraces complexity by representing the invasion as a network and using network structure to inform management locations. We compare optimal versus network-guided invasive species management at a landscape-scale, considering siting of boat decontamination stations targeting 1.6 million boater movements among 9,182 lakes in Minnesota, United States. Studying performance for 58 counties, we find that when full information is known on invasion status and boater movements, the best-performing network-guided metric achieves a median and lower-quartile performance of 100% of optimal. We also find that performance remains relatively high using different network metrics or with less information (median >80% and lower quartile >60% of optimal for most metrics) but is more variable, particularly at the lower quartile. Additionally, performance is generally stable across counties with varying lake counts, suggesting viability for large-scale invasion management. Our results suggest that network approaches hold promise to support sustainable resource management in contexts where modelling capacity and/or data availability are limited. Biological invasions involve complex interactions between social and environmental factors, challenging effective management. This study represents the invasion of Minnesota lakes by zebra mussels as a network of interactions and finds that using network metrics can guide effective management.

Application-centric Network Management - Addressing Safety and Real-time in V2X Applications

Abstract: The current roadmaps and surveys for future wireless networking typically focus on communication and networking technologies and use representative applications to derive future network requirements. Such a benchmarking approach, however, does not cover the application integration challenge that arises from the many distributed applications sharing a network infrastructure, each with their individual topology and data structure. The paper addresses V2X networks as an important example. Crucial end-to-end application constraints including real-time and safety encourage a closer look at application interference and systematic integration. This perspective paper proposes a two-layer resource management that divides the problem into an application integration and a network management task. Valet parking with high-resolution infrastructure camera support is elaborated as a use case that overarches vehicle network and wireless network management. Experiments demonstrate the benefits of complementing the current network-centric management by an application-centric integration.

Network automation

Abstract: In the traditional ways of networking, we have a lot of manual operations to complete any task in networking. This leads to a heavier cost in network management than the cost of the network. To overcome cost and efficiency in network configuration and management, we are automating the tasks using software, where they can control, configure and manage networks. In this project, we are upgrading the Arista device operating system by taking pre and post conformations using python. Networking programming is based on software networks, where scripting is used for network elements control.

AI-driven Service-aware Real-time Slicing for beyond 5G Networks

Abstract: Wide network softwarization is creating fertile ground for the application of novel concepts in the management of the deployed network functions. This allows a drastic shift for the applications hosted on top of the network, as instead of configuring their behaviour to match the network status (network-aware applications) the technology can shift to a self-organizing network that adapts to the hosted applications (service-aware network). In this work, we design, develop and evaluate such a service-aware approach for the telecommunications network. By employing Machine Learning, we are able to classify and predict traffic exchanges made over the network, and appropriately dynamically allocate the slices in the network in real-time. We use as a reference platform the OpenAirInterface framework, and the FlexRAN controller for programming the slice decisions at the RAN level, and evaluate our scheme under real-world settings in a testbed environment.

An Empirical Review of DDOS Attack Mitigation System on SDN Using Cloud Environment

Abstract: The separation of the control plane and the network data plane from the network defined by the software is making it easier for network management. As a result, SDN can be used in a variety of network settings, including network hiring networks. However, the construction of the novel network raises new security issues. Dedicated Shared Denial (DDoS) is easy to distribute and hard to protect on standard networks; on SDN networks, it can bypass the central controllers and bring the entire network down. Cloud computing has emerged as a modern and exciting computer space over the past decade, providing an affordable and awesome computer space. SDN technology combined with cloud computing highlights the challenges of cloud communication and enhances cloud adaptability, configuration, intelligence, and extreme density. Sensitive features of SDN, such as global network coverage, software-based traffic analysis, integrated network management, etc., greatly enhance the acquisition of DDoS cloud capabilities and scalability capabilities. In this study, a major effort was made to compare the various solutions currently available for programs to reduce DDoS attacks in cloud environments using SDN and provided performance tests such as detection rate, recovery time and False positive Rate.

Forecasting for Network Management with Joint Statistical Modelling and Machine Learning

Abstract: Forecasting is a task of ever increasing importance for the operation of mobile networks, where it supports anticipatory decisions by network intelligence and enables emerging zero-touch service and network management models. While current trends in forecasting for anticipatory networking lean towards the systematic adoption of models that are purely based on deep learning approaches, we pave the way for a different strategy to the design of predictors for mobile network environments. Specifically, following recent advances in time series prediction, we consider a hybrid approach that blends statistical modelling and machine learning by means of a joint training process of the two methods. By tailoring this mixed forecasting engine to the specific requirements of network traffic demands, we develop a Thresholded Exponential Smoothing and Recurrent Neural Network (TES-RNN) model. We experiment with TES-RNN in two practical network management use cases, i.e., (i) anticipatory allocation of network resources, and (ii) mobile traffic anomaly prediction. Results obtained with extensive traffic workloads collected in an operational mobile network show that TES-RNN can yield substantial performance gains over current state-of-the-art predictors in both applications considered.

Toward a Trust Aware Network Slice-Based Service Provision in Virtualized Infrastructures

Abstract: Future communication networks such as 5G are expected to support end-to-end delivery of services for several vertical markets with diverging requirements. Network slicing is a key construct that is used to provide end to end logical virtual networks running on a common virtualised infrastructure, which are mutually isolated. Having different network slices operating over the same 5G infrastructure creates several challenges in security and trust. This paper addresses the fundamental issue of trust of a network slice. It presents a trust model and property-based trust attestation mechanisms, which can be used to evaluate the trust of the virtual network functions that compose the network slice. The proposed model helps to determine the trust of the virtual network functions, as well as the properties that should be satisfied by the virtual platforms (both at boot and run time), on which these network functions are deployed for them to be trusted. We present a logic-based language that defines simple rules for the specification of properties and the conditions under which these properties need to be satisfied for trusted virtualized platforms. The proposed trust model and mechanisms enable the service providers to determine the trustworthiness of the network services as well as the users to develop trustworthy applications. We have developed a trust management architecture that enables the service providers to determine the trustworthiness of the network slices providing the network services. We have implemented a prototype of the trust management architecture using the Open Source MANO Platform and presented the performance results. The results show that our trust mechanisms cause only a slight reduction in the performance of network slices over virtualized infrastructure. We have also discussed how the proposed architecture can be used to detect and mitigate the impact of malicious virtual network functions in a dynamic manner.

A High-Performance and Accurate FPGA-Based Flow Monitor for 100 Gbps Networks

Abstract: Network monitoring is important to improve network performance and security. The separation of the data plane and the control plane of SDN gives the network flexibility. This flexibility facilitates network management and gives rise to the need for accurate and fine-grained management of networks. However, the traditional software-based flow monitoring cannot easily keep up with today’s high-speed networks such as 100 GbE, even with the help of high-performance frameworks such as DPDK. To meet the need for fine-grained management of high-speed networks, an accurate hardware-based flow monitor design is presented in this paper. In our design, the FPGA-based pipelined cuckoo hashing is used to achieve efficient storage of flow entries. The flow information is accurately recorded without any sampling. The proposed design can achieve a higher performance than the non-sketch CPU-based methods and higher accuracy than sketch methods. Compared with other state-of-the-art flow monitors, the proposed design can achieve a performance of 100 Gbps while maintaining high accuracy.

Intent-Driven QoS-Aware Routing Management for Flying Ad hoc Networks

Abstract: Flying Ad hoc Network (FANET) is with limited node energy, time-varying dynamic topology, and unstable wire-less links, thus leading to a challenging network management. The network management of the FANET faces frequent network reconfiguration and strict monitoring, which makes the traditional human-involved network management methods unsuitable. Therefore, an autonomous network management method is urgently needed. This paper proposes the intent-driven network management system for FANET, termed as IMF for short. Aiming at the various management intents of FANET, the proposed IMF system explores and exploits intent-driven networking capabilities to improve the network management automation. Through intent translation, policy management, policy verification, and state awareness, the network management intent can be converted into machine-actionable policies at the underlying Unmanned Aerial Vehicles (UAVs) node, which reduces the complexity of network management in a timely and robust way. At last, we present a use case of Quality of Service (QoS)-aware routing management in the proposed IMF system framework. The refined routing intents and the node state information are stored and transmitted in the re-designed time slot reservation request (TREQ) and topology control (TC) packets. A proof of concept of the implementation platform is built to verify the effective control and management of the presented intent-driven QoS-aware routing management.

Edge-Powered In-Network Processing for Content-Based Message Management in Software-Defined Industrial Networks

Abstract: Traditional industrial networks were characterized by flat topologies, where industrial equipment exchanged a limited number of messages. In sharp contrast, modern manufacturing plants are evolving towards articulated environments generating an ever-increasing amount of network traffic. Such emerging environments prevent the adoption of traditional solutions based on end-to-end dispatching of few messages in reliable networks with bandwidth availability much greater than needed. This leads to the need to adopt proper message management strategies as close as possible to industrial equipment to avoid overwhelming the industrial network with non-mission-critical traffic at the expense of mission-critical one. This paper originally proposes edge-powered in-network processing to i) transparently manage messages sent by industrial equipment, ii) support a broad spectrum of message management strategies, ranging from efficient header-based solutions to expressive content-based ones, and iii) fulfill the application-dependent requirements demanded by industrial environments nowadays. Achieved performance results based on a proof-of-concept prototype demonstrate that the proposed solution efficiently provides content-based message management at the edge, even considering edge nodes with limited hardware capabilities.

Network Perspective in Megaproject Management: A Systematic Review

Abstract: Megaproject management has continuously faced new challenges that require new theories and methods. The network perspective has been an increasing trend in this context. However, there is a lack of consensus concerning the applicability of network thinking to megaprojects and the status of network analytic methods with respect to the facilitation of megaproject management. This paper aims to present the full status of the network perspective in the context of megaproject management, integrate network thinking, clarify the application of network analytic methods, and accelerate the network paradigm in the context of megaproject management. This research included a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analyses framework. A total of 152 relevant studies were retrieved from three major databases and reviewed. The findings of this study were based on a novel integrated framework that included the constitutive and the analytic perspectives of the network paradigm. The constitutive perspective sheds light on the megaproject network, its definition, characteristics pertaining to network thinking, and megaproject governance through network logic. The analytic perspective illuminates the applicability of network methods to megaproject issues in detailed subknowledge areas, including stakeholder management, risk management, communication, coordination and collaboration, knowledge management, and interface management. Furthermore, these two perspectives were generalized and converged into pure categories of network research, including network mechanisms and antecedents, network patterns and dynamics, network functions and outcomes, and network controls and optimization. Based on meticulous discussions concerning the integrated framework, limitations and future directions for progress in this area were proposed to facilitate a deeper exchange of ideas in the context of any future research efforts.

Integrating of Promising Computer Network Technology with Intelligent Supervised Machine Learning for Better Performance

Abstract: The Software defined network (SDN) controller has such networks universal sight and allows for centralized management and control for the networks. The algorithms of Machine learning used alone or combined with the SDN controller's northbound applications in order to make intelligent SDN. SDN is such potential networking design that blends network's programmability with central administration. The control and the data planes are separated in SDN, and the network with central management point is called SDN controller, which may be programmed and utilized as a brain of the network. Lately, the community of researchers have shown a greater willingness to take advantage of current advances in artificial intelligence to give the SDN best decision making and learning skills. Our research found that combining SDN with Intelligent Supervised Machine Learning (ISML) is very important for performance improvement. ISML is the development of algorithms that can generate broad patterns and assumptions from external source instances in order to portend the predestination of future instances. The ISML algorithms of classification goal is to categorize data based on past information. In data science problems, classification is used rather frequently. To solve such problems, a number of successful approaches were already presented, including rule-based techniques, instance-based techniques, logic-based techniques, and stochastic techniques. This study examined the ISML algorithms' efficiency by checking the precision, accuracy, and with or without SDN recall.