5G SLICING

5G StandAlone (SA):
The next wave of connectivity

The mobile network landscape is undergoing a transformative shift as the industry transitions from hybrid networks (non-standalone 5G) to standalone 5G technology. This evolution represents a significant milestone in the pursuit of advanced connectivity, enabling a wide range of new use cases.

Moreover, the consolidation of 5G Standalone promises unprecedented improvements in speed, latency, and capacity, paving the way for innovations that will revolutionize industries and enhance daily lives.

5G SA terminals will communicate and exchange data exclusively over the 5G network, leveraging the performance and capabilities of the new standard immediately and without delays, thereby reducing the load on the existing 4G network.

Can I have a Slice? Introduction on 5G Network Slicing

The key distinction between 5G Non-Standalone (NSA) and 5G Standalone (SA) is in network configuration and performance. 5G NSA uses both the 5G New Radio Base Station (gNB) and the 4G Evolved Node B (eNB), leveraging existing 4G infrastructure for a quicker, cost-effective rollout but with limited 5G performance. 5G SA, on the other hand, deploys an independent 5G network, unlocking 5G's full potential. It enables efficient and flexible network management through network slicing, which is a key factor of 5GSA habilitation as it allows operators to create specialized virtual networks for different applications unlocked from the 5G SA.

A network slice is defined as a logical (virtual) network customized to serve a defined business purpose or customer, each slice encompasses an independent set of logical network functions to satisfy the specific performance and economic needs of that service class or customer application.

Innovative Architecture and Network Slicing in 5G

Characteristics and Advantages

Within this innovative concept, it is possible to create multiple virtual independent networks on top of a shared physical network infrastructure, where on-demand customization is available, by assuring:

• Isolation

• Guaranteed performance

• Scalability

• Support for multi-vendor

• Support for multiple-operator scenarios


Additionally, Service-Based Architecture (SBA), that decomposes the 5G core network into smaller, independently deployable services known as network functions (NFs), is a driver for the development of network slicing.

This technology supports the transformation of the network from silos over monoliths towards slices and it is critical to meet key requirements of 5G SA:

• Ultra Reliable Low Latency Communications (uRLLC): this involves applications with stringent requirements for throughput, latency, and availability

• Massive Machine Type Communication (mMTC): services involving a large number of devices not particularly sensitive to delay

• Enhanced Mobile Broadband (eMBB): this service refers to new application areas and requirements that provide a smoother user experience through high traffic capacity and high data rates, along with continuous coverage and high user mobility.

Business Opportunities

Key Target Markets and Potential Use Cases

Communication Service Providers (CSPs) are leveraging network slicing to develop new services and applications that share several key implementation requirements:

• High-speed video transmission: essential for telemedicine, remote health assessment, teleoperated vehicles, and remote inspections in energy/utilities;

• (Ultra) Low latency: crucial for the command/control of teleoperated vehicles, remote surgery, and AR/VR applications;

Network slicing enhances infrastructure and develops new scenarios in the B2B context, with commercialization decisions driven by customer appeal, public relations impact, and economic considerations. The key markets are as follows:

• High availability: necessary during periods of network congestion;

• Enhanced security: important for services with critical impacts.

Network slicing enhances infrastructure and develops new scenarios in the B2B context, with commercialization decisions driven by customer appeal, public relations impact, and economic considerations.

See the box below for information on key markets.


The role of Edge Computing and AI to 5G Network Slicing commercialization

Advances in machine learning (ML) and artificial intelligence (AI) technologies will enable new levels of efficiency in 5G slices management. These technologies will facilitate the transition from manual to fully automated processes, enabling proactive maintenance and optimization of network performance.

Some key points on how AI and ML could be used in network slicing:

• Dynamic Resource Allocation: AI algorithms can dynamically allocate network resources to different slices to accommodate specific needs.

• Predictive Maintenance: ML agents on each slice collect data and use that for prediction and root-cause analysis to identify reliable and fast solutions and dynamically reallocate network resources.

• Traffic Management: ML models analyze traffic patterns to predict peak demand and adjust network resources accordingly, ensuring that each network slice maintains its quality of service (QoS) requirements even during peak usage times.

• Security Enhancement: AI proactively addresses potential network failures, enhancing reliability and minimizing downtime. It also dynamically enhances network security, generating and applying updated policies across the network to defend against evolving threats.

AI and ML will optimize 5G networks by addressing dynamic resource allocation and reallocation through an automated network healing process, striking a balance between efficiency and user experience. To achieve the QoS and SLA for 5G Network Slicing we can consider various Machine Learning methods to boost the Slice Allocation Mechanism of the following architecture:


In particular, Network Slicing can be modeled as a Classification problem. In Machine Learning, Classification is a method where the model tries to predict the label of the input data. Classification models are fully trained using the training data, subsequently the model is evaluated on test data and, lastly, we can use it to perform predictions on new unknown data. For Network Slicing, an algorithm can learn to predict the correct Slice based on network data that characterizes the related service.


RANDOM FOREST

SUPPORT VECTOR MACHINE

K-NEAREST NEIGHBOURS

DECISION TREE
CLICK ON EACH BOX TO DISCOVER THE MAIN CLASSIFICATION ALGORITHMS

RANDOM FOREST


is an ensemble learning method for classification and regression problems that operates by constructing decision trees. In prediction, the algorithm aggregates the result of all trees by voting for classification tasks.

SVM


is a Supervised Learning model that analyzes data for classification based on the concept of decision planes.

KNN


is a non-parametric method used for classification and regression. It is one of the basic classification algorithms that belongs to the supervised learning domain.

DECISION TREE


is a computation model in which comparisons based branching operation is used. It is a type of supervised learning algorithm that is widely used in classification problems.

NET REPLY'S ROLE

Net Reply accelerates the development of use cases for network slicing by leveraging technologies such as Edge computing, AI, and advanced tools for configuration and slice optimization. In addition, Net Reply supports innovative use cases such as the deployment of specialized services through BoxNET, which can easily and quickly configure temporary networks based on different technologies and thus without requiring new hardware from the customer. This flexibility enables innovative solutions in different areas, making Net Reply a key facilitator in efficient slice management and continuous innovation of network services.


Contact us

Before filling out the registration form, please read the Privacy notice pursuant to Article 13 of EU Regulation 2016/679
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input

Privacy

I declare that I have read and fully understood the Privacy Notice and I hereby express my consent to the processing of my personal data by Reply SpA for marketing purposes, in particular to receive promotional and commercial communications or information regarding company events or webinars, using automated contact means (e.g. SMS, MMS, fax, email and web applications) or traditional methods (e.g. phone calls and paper mail).