Internet of Things (IoT) is an emerging technology that makes people’s lives smart by conquering a plethora of diverse application and service areas. In near future, the fifth-generation (5G) wireless networks provide the connectivity for this IoT ecosystem. It has been carefully designed to facilitate the exponential growth in the IoT field. Network slicing is one of the key technologies in the 5G architecture that has the ability to divide the physical network into multiple logical networks (i.e., slices) with different network characteristics. Therefore, network slicing is also a key enabler of realisation of IoT in 5G. Network slicing can satisfy the various networking demands by heterogeneous IoT applications via dedicated slices. In this survey, we present a comprehensive analysis of the exploitation of network slicing in IoT realisation. We discuss network slicing utilisation in different IoT application scenarios, along with the technical challenges that can be solved via network slicing. Furthermore, integration challenges and open research problems related to the network slicing in the IoT realisation are also discussed in this paper. Finally, we discuss the role of other emerging technologies and concepts, such as blockchain and Artificial Intelligence/Machine Learning (AI/ML) in network slicing and IoT integration.

https://researchrepository.ucd.ie/bitstream/10197/12083/2/IEEE_COMST_Slicing___IoT_survey__Final_Submission__%20%281%29.pdf

Survey on Network Slicing for Internet of Things Realization in 5G Networks

Recent advances in the Internet of Things (IoT) are giving rise to a proliferation of interconnected devices, allowing the use of various smart applications The enormous number of IoT devices generates a large volume of data that requires further intelligent data analysis and processing methods such as deep learning (DL) Notably, DL algorithms, when applied to the Industrial IoT (IIoT), can provide various new applications, such as smart assembling, smart manufacturing, efficient networking, and accident detection and prevention Motivated by these numerous applications, in this article, we present the key potentials of DL in IIoT First, we review various DL techniques, including convolutional neural networks, autoencoders, and recurrent neural networks, as well as their use in different industries We then outline a variety of DL use cases for IIoT systems, including smart manufacturing, smart metering, and smart agriculture We delineate several research challenges with the effective design and appropriate implementation of DL-IIoT Finally, we present several future research directions to inspire and motivate further research in this area

Deep Learning in the Industrial Internet of Things: Potentials, Challenges, and Emerging Applications

Network Slicing will play a vital role in enabling a multitude of 5G applications, use cases, and services. Network slicing functions will provide an end-to-end isolation between slices with an ability to customize each slice based on the service demands (bandwidth, coverage, security, latency, reliability, etc.). Maintaining isolation of resources, traffic flow, and network functions between the slices is critical in protecting the network infrastructure system from Distributed Denial of Service (DDoS) attack. The 5G network demands and new feature sets to support ever-growing and complex business requirements have made existing approaches to network security inadequate. In this paper, we have developed a Neural Network based ‘Secure5G’ Network Slicing model to proactively detect and eliminate threats based on incoming connections before they infest the 5G core network. ‘Secure5G’ is a resilient model that quarantines the threats ensuring end-to-end security from device(s) to the core network, and to any of the external networks. Our designed model will enable the network operators to sell network slicing as-a-service to serve diverse services efficiently over a single infrastructure with high security and reliability.

Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond

Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user. The increased speeds and reduced delay enable novel applications such as connected vehicles, large-scale IoT, video streaming, and industry robotics. Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically scaling up network resources as needed. Together, mobile edge computing and ML enable seamless automation of network management to reduce operational costs and enhance user experience. In this paper, we discuss the state of the art for ML within mobile edge computing and the advances needed in automating adaptive resource allocation, mobility modeling, security, and energy efficiency for 5G networks.

Deep Learning at the Mobile Edge: Opportunities for 5G Networks

Optimal 5G network slicing using machine learning and deep learning concepts

Existing cellular communications and the upcoming 5G mobile network requires meeting high-reliability standards, very low latency, higher capacity, more security, and high-speed user connectivity. Mobile operators are looking for a programmable solution that will allow them to accommodate multiple independent tenants on the same physical infrastructure and 5G networks allow for end-to-end network resource allocation using the concept of Network Slicing (NS). Data-driven decision making will be vital in future communication networks due to the traffic explosion and Artificial Intelligence (AI) will accelerate the 5G network performance. In this paper, we have developed a ‘DeepSlice’ model by implementing Deep Learning (DL) Neural Network to manage network load efficiency and network availability, utilizing in-network deep learning and prediction. We use available network Key Performance Indicators (KPIs) to train our model to analyze incoming traffic and predict the network slice for an unknown device type. Intelligent resource allocation allows us to use the available resources on existing network slices efficiently and offer load balancing. Our proposed DeepSlice model will be able to make smart decisions and select the most appropriate network slice, even in case of a network failure.

DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks

The Internet of Things (IoT) is poised to revolutionize how people, industries, and enterprises connect to customers and individuals. Network Protocols, Technology and Standards such as Narrowband IoT (NB-IoT), LTE-M, 5G, LoRaWAN, Message Queue Telemetry Transport (MQTT), Constrained Application Protocol (CoAP), Device management such as Open Mobile Alliance (OMA) for Machine to Machine (M2M) are being developed to support a variety of IoT applications and services. IoT ecosystem is creating tremendous business opportunities and opening the doors for innovation. With the explosive growth of connected devices, approximately five quintillion bytes of data is estimated to be generated by the Internet every day. Not all these connections and ecosystems are secure; the security vulnerabilities are steadily increasing in parallel due to the lack of secure updating mechanisms especially for IoT ecosystem. This paper proposes three different models using the CoAP and MQTT application protocol, which aims at providing efficient mechanisms and methods for Over the Air delivery of Software Updates and Security Patches to IoT devices and evaluates which protocol is better suited for proposed models and applications.

CoAP and MQTT Based Models to Deliver Software and Security Updates to IoT Devices over the Air

A mobile communication device that replenishes and manages ads to display on an active application. The mobile communication device comprises a radio transceiver, a processor, a memory, a plurality of applications, stored in the memory, wherein each application comprises an ad client, and an ad manager, stored in the memory. The ad manager, when executed by the processor, requests a plurality of ads from an ad gateway associated with the network associated with the mobile communication device. The ad manager then receives a plurality of ads from the ad gateway. The ad manager then stores these ads into an ad cache, embedded within the memory of the mobile communication device. The ad manager receives a request from an ad client of one of the applications for an ad to display. The ad manager sends an ad selected from the ad cache to the ad client in the active application.

Anurag Thantharate

Papers

DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks

Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond

CoAP and MQTT Based Models to Deliver Software and Security Updates to IoT Devices over the Air

Ad management using ads cached on a mobile electronic device

ADAPTIVE6G: Adaptive Resource Management for Network Slicing Architectures in Current 5G and Future 6G Systems