Implementing Machine Learning Techniques for Artificial Neural Networks in 5G Network Quality of Service Management (original) (raw)
Related papers
On Concept of Artificial Intelligence for Quality of Service Management in 5G Network
Academia Letters, 2022
The scenario for 5G-New Radio multimedia is one in which communication transparency is expected across integrated but disparate types of networks. A common problem with all such heterogeneous platforms is how to equitably allocate the limited network resource that is available to competing applications. Quality of Service (QoS) is a transcendental perception of how fairly resources are shared to end users. It translates from the degree of satisfaction a subscriber gets, and is a function of the agility of network response to potential violations of agreed regulatory parameters. This short paper describes a conceptual architecture for managing access within the data plane of 5G network. A new memory-based artificial intelligence cognitive engine is proposed. The concept is to achieve fast multi-service QoS improvements by mapping the probabilistic signature of a combination of resource allocation characteristics to the end-user soft QoS demands.
Empowering the Future 5G Networks: An AI based Approach
Telecom Business Review: SITM Journal, 2017
The next telecommunications standard, 5G, envisions that the future networks will support advanced use cases, such as Internet of things while supporting voluminous simultaneous connections with high bandwidth as well as low latency. Further, these 5G deployments will not be static in nature, with new use cases and service requirements evolving in future. Such requirements pose many deployment and operational challenges to MNOs. These use cases would not only require the networks to be aware of connectivity related parameters, but also adapt intelligently based on parameters beyond the network. This requires the 5G networks to be capable of addressing conditions which are not foreseen at the time of designing them. Such capability requirements can be adequately addressed by advances in the field of AI and machine learning. The objective of this paper is to explore ways to leverage AI and machine learning for enhancing the 5G network deployments and operations. This paper attempts to decipher future demands from the 5G networks analyzing specific requirements in the areas of network planning, network operations and network optimization. This paper also discusses the strategic perspective for MNOs to benefit from applications of AI in 5G networks.
Artificial Intelligence-based 5G Network Capacity Planning and Operation
The highly demanding requirements envisaged for future 5G networks together with the required support of new customers from vertical industries (e.g. e-health, automotive, energy) pose a big challenge for operators in 5G on how to balance investments, user experience and profitability. There will be the need to revisit the actual methodologies of network planning and operation, fully exploiting cognitive capabilities that embrace knowledge and intelligence to achieve a proper understanding of the network usage in multiple dimensions. In this respect, this paper presents a vision on how these planning and operation processes can rely on the inclusion of Artificial Intelligence (AI) concepts that will allow devising models to characterize the impact of many correlated inputs on specific operator objectives and to drive decisions for different processes.
Artificial Intelligence in 5G Technology: Overview of System Models
Asia Pacific Journal of Energy and Environment, 2021
The occurrence of various devices that are interlinked to provide advanced connectivity throughout the systems revolves around the formation of 5G systems. Artificial Intelligence plays a fundamental role in the 5G networks. The popularity and integration of 5G have emerged through advanced cellular networks and many other technologies. This innovative and speedy network has built strong connections in recent years, its conduct in business, personal work, or daily life. Artificial Intelligence and edge computing devices have optimized internet usages in everyday life. The growth of 5G networks is effective in the AI/ML algorithms due to its low latency and high bandwidth, which also performs real-time analysis, reasoning, and optimization. The 5G era has fundamental features that are highlighted among the revolutionary techniques which are most commonly used by cellular device networks, such as the resource management of radio, mobility management, and service management, and so on....
Implanting Intelligence in 5G Mobile Networks—A Practical Approach
Electronics
With the advancement in various technological fronts, we are expecting the design goals of smart cities to be realized earlier than expected. Undoubtedly, communication networks play the crucial role of backbone to all the verticals of smart cities, which is why we are surrounded by terminologies such as the Internet of Things, the Internet of Vehicles, the Internet of Medical Things, etc. In this paper, we focus on implanting intelligence in 5G and beyond mobile networks. In this connection, we design and develop a novel data-driven predictive model which may serve as an intelligent slicing framework for different verticals of smart cities. The proposed model is trained on different machine learning algorithms to predict the optimal network slice for a requested service resultantly assisting in allocating enough resources to the slice based on the traffic prediction.
Artificial Intelligence for Elastic Management and Orchestration of 5G Networks
IEEE Wireless Communications, 2019
The emergence of 5G enables a broad set of diversified and heterogeneous services with complex and potentially conflicting demands. For networks to be able to satisfy those needs, a flexible, adaptable, and programmable architecture based on network slicing is being proposed. Moreover, a softwarization and cloudification of the communications networks is required, where network functions (NFs) are being transformed from programs running on dedicated hardware platforms to programs running over a shared pool of computational and communication resources. This architectural framework allows the introduction of resource elasticity as a key means to make an efficient use of the computational resources of 5G systems, but adds challenges related to resource sharing and efficiency. In this paper, we propose Artificial Intelligence (AI) as a built-in architectural feature that allows the exploitation of the resource elasticity of a 5G network. Building on the work of the recently formed Experiential Network Intelligence (ENI) industry specification group of the European Telecommunications Standards Institute (ETSI) to embed an AI engine in the network, we describe a novel taxonomy for learning mechanisms that target exploiting the elasticity of the network as well as three different resource elastic use cases leveraging AI. This work describes the basis of a use case recently approved at ETSI ENI.
Performance Analysis of Resource Allocation in 5G & Beyond 5G using AI
In the foreseeable future, the increase in the number of devices and the Internet of Things (IoT) can make it troublesome for the latest cellular networks to make sure adequate network resources are allocated. Future network technologies have attracted increasing attention, by delivering new style ideas with dynamic resource allocation. Device resource requirements are typically variable, so a dynamic resource allocation methodology is adapted to ensure the efficient execution of any task. In this project, Performance Analysis of Resource Allocation in Future Cellular Networks with AI an attempt has been made to replicate a modern cellular data structure that supports dynamic resource allocation. Therefore, we will be designing a modern cellular data structure that supports dynamic resource allocation. Then, a dynamic nested neural network is built, which adjusts the nested learning model structure online to meet the training necessities of dynamic resource allocation. An AI-driven dynamic resource allocation algorithm (ADRA) is used that supports the nested neural network combined with the Markov decision process for training a Modern cellular data structure. The results will thus validate that the algorithm improves the average resource hit rate and reduces the average delay time.
A QoE-oriented cognition-based management system for 5G slices: The SliceNet approach
2019
Provisioning of network slices with appropriate Quality of Experience (QoE) guarantees is one of the key enablers for 5G networks. However, it poses several challenges in the slice management that need to be addressed to achieve an efficient end-to-end (E2E) services delivery. These challenges, among others, include the estimation of QoE Key Performance Indicators (KPIs) from monitored metrics and the corresponding reconfiguration operations (actuations) in order to support and maintain the desired quality levels. In this context, SliceNet provides a design and an implementation of a cognitive slice management framework that leverages machine learning (ML) techniques in order to proactively maintain network conditions in the required state that assures E2E QoE, as perceived by the vertical customers.
2020
The advent of the wireless communications systems augurs new cutting-edge technologies, including self-driving vehicles, unmanned aerial systems, autonomous robots, Internet-of-Things, and virtual reality. These technologies require high data rates, ultra-low latency, and high reliability, all of which are promised by the fifth generation of wireless communication systems (5G). Many research groups state that 5G cannot meet its demands without artificial intelligence (AI) integration as 5G wireless networks are expected to generate unprecedented traffic giving wireless research designers access to big data that can help in predicting the demands and adjust cell designs to meet the users requirements. Subsequently, many researchers applied AI in many aspects of 5G wireless communication design including radio resource allocation, network management, and cyber-security. In this paper, we provide an in-depth review of AI for 5G wireless communication systems. In this respect, the aim o...
2020 10th Annual Computing and Communication Workshop and Conference (CCWC), 2020
The advent of the wireless communications systems augurs new cutting-edge technologies, including self-driving vehicles, unmanned aerial systems, autonomous robots, the Internet of-Things, and virtual reality. These technologies require high data rates, ultra-low latency, and high reliability, all of which are promised by the fifth generation of wireless communication systems (5G). Many research groups state that 5G cannot meet its demands without artificial intelligence (AI) integration as 5G wireless networks are expected to generate unprecedented traffic giving wireless research designers access to big data that can help in predicting the demands and adjust cell designs to meet the users' requirements. Subsequently, many researchers applied AI in many aspects of 5G wireless communication design including radio resource allocation, network management, and cyber-security. In this paper, we provide an in-depth review of AI for 5G wireless communication systems. In this respect, the aim of this paper is to survey AI in 5G wireless communication systems by discussing many case studies and the associated challenges, and shedding new light on future research directions for leveraging AI in 5G wireless communications.