6G networks: An introduction and a context-aware caching scheme for edge networks

Noman Islam

Professor

Karachi Institute of Economics and Technology, Pakistan

4 April 2022

Introduction

• Mobile communication progresses with a new generation every 10 years
• Cisco predicted that by 2023 there will be 14.7 billion devices connect to IoT with various applications that are generating a huge volume of data.
• Moreover, the popularity of multimedia services over wireless networks is exploding.
• Therefore, supporting such a volume of data demands new generations of cellular networks due to the limitation of the previous generations

6G networks: An introduction and a context-aware caching scheme for edge networks

Generations of mobile phone

6G networks: An introduction and a context-aware caching scheme for edge networks

Introduction

• Following this trend, in 2030 and beyond, 6G will evolve
• It will provide ubiquitous AI services from the core to the end devices of the network

​

6G networks: An introduction and a context-aware caching scheme for edge networks

Introduction

• 6g will provide support for intelligent network orchestration and management
• AI will play a critical role in designing and optimizing 6G architectures, protocols, and operations

6G networks: An introduction and a context-aware caching scheme for edge networks

6G networks: An introduction and a context-aware caching scheme for edge networks

Source: [4]

Just a little background 5G

• 5G uses several revolutionary technologies, e.g.,
• higher frequencies,
• network function virtualization (NFV),
• software defined networking (SDN),
• and network slicing
• massive multiple-input and multiple-output (MIMO)

6G networks: An introduction and a context-aware caching scheme for edge networks

5g applications

• Meanwhile, 5G network is used in a wide range of applications such as:
• IoT,
• smart city,
• Industry 4.0,
• e-health,
• wearables,
• smart utilities

6G networks: An introduction and a context-aware caching scheme for edge networks

5g use cases

• The main 5G service classes include:
• enhanced mobile broadband (eMBB),
• ultra-reliable low latency communications (URLLC),
• massive machine type communication (MTC) (MTC).

​

​

6G networks: An introduction and a context-aware caching scheme for edge networks

The need for 6g

• 5g will not able to meet connection density (10 million connections / km²)
• Novel paradigms such as extended reality, flying cars, mind machine interface, telemedicine
• Increasing complexity of the network with heterogeneous devices

6G networks: An introduction and a context-aware caching scheme for edge networks

Key technologies

• Besides AI, there will be a number of other technologies that will play a key role in 6g networks
• This includes:
• Block chain
• Visible light communication
• Tera Hertz communication
• Edge computing

6G networks: An introduction and a context-aware caching scheme for edge networks

6G vision

6G vision

• 6G will:
• connect everything,
• provide full dimensional wireless coverage, and
• integrate all functions, including sensing, communication, computing, caching, control, positioning, radar, navigation, and imaging, to support full-vertical applications.

6G networks: An introduction and a context-aware caching scheme for edge networks

Multi dimensional coverage

• According to [2], 6G will not be limited to terrestrial communication networks
• It will need to be complemented with non-terrestrial networks such as satellite and unmanned aerial vehicle (UAV) communication networks, thus achieving a space-air-ground-sea integrated communication network.

6G networks: An introduction and a context-aware caching scheme for edge networks

6G networks: An introduction and a context-aware caching scheme for edge networks

Terahertz communication

• Different spectra will be fully explored to further increase data rates and connection density, including the:
• sub-6 GHz,
• millimeter wave (mmWave),
• terahertz (THz), and
• optical frequency bands

6G networks: An introduction and a context-aware caching scheme for edge networks

Smart applications

• 6G networks will enable a new range of smart applications with the aid of artificial intelligence (AI) and big data technologies.
• This includes:
• Smart city
• Smart health
• Smart education
• However, network security will have to be strengthened when developing 6G networks

6G networks: An introduction and a context-aware caching scheme for edge networks

6G networks: An introduction and a context-aware caching scheme for edge networks

6G properties

• 6G will be transformative and will revolutionize the wireless evolution from “connected things” to “connected intelligence
• Very high data rates, up to 1 Tb/s;
• Very high energy efficiency, with the ability to support battery-free IoT devices;
• Massive low-latency control (less than 1 msec end-to-end latency);
• Very broad frequency bands (e.g., 73GHz- 140GHz and 1THz-3THz

6G networks: An introduction and a context-aware caching scheme for edge networks

6G properties

• Ubiquitous always-on broadband global network coverage by integrating terrestrial wireless with satellite systems;
• Connected intelligence with machine learning capability

​

6G networks: An introduction and a context-aware caching scheme for edge networks

6G use cases

• According to [4], the possible use cases of 6g will be:
• Augmented and virtual reality
• Holographic telepresence
• eHealth
• Pervasive connectivity
• Industry 4.0

6G networks: An introduction and a context-aware caching scheme for edge networks

Recent developments

• In 2020, scientists from the Nanyang Technological University in Singapore and Osaka University in Japan announced they had created a chip for terahertz (THz) waves, which might be used in 6G
• In January 2022, Purple Mountain Laboratories of China claimed that its research team had achieved a world record of 206.25 gigabits per second (Gbit/s) data rate for the first time in a lab environment within the terahertz frequency band which is supposed to be the base of 6G cellular technology

6G networks: An introduction and a context-aware caching scheme for edge networks

• On November 6, 2020, China successfully launched an experimental test satellite with candidates for 6G technology into orbit, along with 12 other satellites, using a Long March 6 launch vehicle rocket

6G networks: An introduction and a context-aware caching scheme for edge networks

The role of AI

Network intelligentization

• In 5G, the two key 5G technologies are Software-Defined Networking (SDN) and Network Functions Virtualization (NFV), which have moved modern communications networks toward software-based virtual networks.
• Softwarization is not going to be sufficient for 6G
• The network entities have to support diverse capabilities, including communications, content caching, computing, and even wireless power transfer.

6G networks: An introduction and a context-aware caching scheme for edge networks

Software defined networks

6G networks: An introduction and a context-aware caching scheme for edge networks

Edge computing

6G networks: An introduction and a context-aware caching scheme for edge networks

Intelligent radios

• Spectrum sensing is an important technique to improve the spectrum usage efficiency and address spectrum scarcity problems.
• In this case, AI technologies can be applied to identify the spectrum characteristics, and intelligently establish suitable training models to sense spectrum working status.

6G networks: An introduction and a context-aware caching scheme for edge networks

Cognitive radios

6G networks: An introduction and a context-aware caching scheme for edge networks

Machine learning

• It is costly to transmit or store the massive raw data in dense networks.
• Hence, it is necessary to reduce data dimension of the raw data, filter abnormal data, and finally achieve a more reasonable dataset.
• AI-based techniques such as PCA and ISOMAP, are two common AI algorithms which can help 6G networks to transform higher-dimensional data into a lower-dimensional subspace

6G networks: An introduction and a context-aware caching scheme for edge networks

Data analytics

• On the other hand, data analytics is responsible for intelligently analyzing the collected data to discover useful information and form valuable knowledge.

​

6G networks: An introduction and a context-aware caching scheme for edge networks

Opportunities using data analytics

• Data analytics has brought us an excellent opportunity to :
• understand the essential characteristics of wireless networks,
• and achieve more clear and in-depth knowledge of the behavior of 6G networks,
• finally valuable patterns or rules can be discovered as knowledge to provide suitable solutions for resource management, protocol adaptation, architecture, slicing, cloud computing, signal processing, and so on.

6G networks: An introduction and a context-aware caching scheme for edge networks

Mobility modelling

• For instance, based on the discovered knowledge, one would be able to efficiently understand the mobility patterns of UAVs in the sky, establish the channel path loss model of satellite-ground link, and predict the device behavior in ground networks [1]

6G networks: An introduction and a context-aware caching scheme for edge networks

Smart applications

• Smart city, smart industry, smart transportation, smart grid and smart health, and handle global management relevant to all smart type applications. [1]
• All the activities of smart devices, terminals and infrastructures in 6G networks are also managed by the smart application layer through the AI techniques to realize network self-organization ability

6G networks: An introduction and a context-aware caching scheme for edge networks

Big data analytics

• There are four types of analytics that can be applied to 6G
• Descriptive analytics mine historical data to get insights on network performance, traffic profile, channel conditions, user perspectives, and so on. It greatly enhances the situational awareness of network operators and service providers.
• Diagnostic analytics enable autonomous detection of network faults and service impairments, identify the root causes of network anomalies, and ultimately improve the network reliability and security.

6G networks: An introduction and a context-aware caching scheme for edge networks

• Predictive analytics use data to predict future events such as traffic patterns, user locations, user behavior and preference, and resource availability.
• Prescriptive analytics take advantage of the predictions to suggest decision options for resource allocation, network slicing and virtualization, cache placement, edge computing, and so on.

​

6G networks: An introduction and a context-aware caching scheme for edge networks

Intelligent mobility and handover

• AI techniques can be adopted to intelligently achieve mobility prediction and optimal handover solutions to guarantee communication connectivity [1]

6G networks: An introduction and a context-aware caching scheme for edge networks

Security and privacy

• It is worth noting that harvesting and analyzing a large amount of data raise concerns about data security, privacy, ethics, and ownership.
• Hence, the 6G architecture and protocols shall be designed in a way that protects data security, privacy and integrity.
• At the same time, it is equally important that laws and regulations are established to address data ethics and ownership in the context of 6G, bearing in mind the need for a proper balance between risk and benefit.

6G networks: An introduction and a context-aware caching scheme for edge networks

Use of novel spectrum

VLC communication

• 6G networks are expected to rely on conventional spectrum (i.e., sub-6 GHz and mmWaves) but also on frequency bands that have not yet been considered for cellular standards, namely the terahertz band and visible light communications (VLC)

6G networks: An introduction and a context-aware caching scheme for edge networks

TeraHertz communication

• TeraHertz operate between 100 GHz and 10 THz and, compared to mmWaves, bring to the extreme the potential of high-frequency connectivity, enabling data rates on the order of hundreds of gigabits per second, in line with the boldest 6G requirements.

6G networks: An introduction and a context-aware caching scheme for edge networks

Issues with Tera Hertz band

• On the other side, the main issues that have prevented the adoption of terahertz links in commercial systems so far are propagation loss, molecular absorption, high penetration loss, and engineering challenges for antennas and radio frequency (RF) circuitry

6G networks: An introduction and a context-aware caching scheme for edge networks

Solutions

• As for mmWaves, the propagation loss can be compensated using directional antenna arrays, also enabling spatial multiplexing with limited interference.
• Furthermore, terahertz communication performance can be maximized by operating in frequency bands not severely affected by molecular absorption

6G networks: An introduction and a context-aware caching scheme for edge networks

AI based edge computing

AI powered mobile edge computing

• Transforms mobile communication networks into distributed cloud computing platforms.
• Refers to the deployment and execution of distributed computing capabilities, content caching, and network data analytics and network decisions making at the network edge
• Evolution of MEC toward an AI enabled platform [3]
• Computationally efficient dedicated hardware capable of running locally ML/AI Algorithms at the edge devices

6G networks: An introduction and a context-aware caching scheme for edge networks

A novel technique for caching at the edge

Caching at the edge

• Most of the requests on mobile/ cellular networks are for videos or social media contents
• Popular contents can be cached
• Where to cache?
• Cache at the edge on small base stations or mobile terminals

6G networks: An introduction and a context-aware caching scheme for edge networks

Increasing demand for data

• Rise in computing devices, connectivity medium
• How to cope with soaring demands for data?
• Capacity can be increased by installing more access points or base stations
• There is a limit to the network densification
• Most of the contents are videos or social media data

6G networks: An introduction and a context-aware caching scheme for edge networks

Caching at the edge in the network

• If the popular contents (such as videos) can be proactively cached at the edges closer to the user, the backhaul network can be offloaded.
• Caching can not only avoid the network congestion but also reduce the latency incur in response to user request.

6G networks: An introduction and a context-aware caching scheme for edge networks

Current approaches

6G networks: An introduction and a context-aware caching scheme for edge networks

Collaborative filtering

• Collaborative filtering is based on the idea that people who liked similar things in past would likely to have same opinion about future items.
• Collaborative filtering approaches are classified as neighborhood based and latent factor approaches.
• The former finds a set of neighbors to a user or item. While in latent factor approach, the rating of a user is decomposed using matrix factorizing technique.

6G networks: An introduction and a context-aware caching scheme for edge networks

Bastug et al. [5]

• Bastug et al. have proposed an approach based on recommendation system for caching in 5G network.
• A popularity matrix is calculated by solving a least square problem.
• The regularized singular value decomposition was chosen to decompose the popularity matrix into two sub-matrices.

6G networks: An introduction and a context-aware caching scheme for edge networks

Popularity matrix

6G networks: An introduction and a context-aware caching scheme for edge networks

Context-aware collaborative filtering

• In the established domain of CF, context-aware approaches already exist
• They are classified as contextual pre-filtering, contextual post-filtering and contextual modeling
• We suggest employing these techniques to Bastug et al.

6G networks: An introduction and a context-aware caching scheme for edge networks

TF-based context-aware collaborative filtering

• The demands for data items of a particular user are predictable based on a popularity matrix P
• Each small cell base station is equipped with storage capabilities M to cache the popular contents.
• As the storage available is small, a popularity matrix P is used to decide what particular contents to be cached.
• It is also assumed that the user arrives randomly in the network and the file samples to be cached are drawn from ZipF(α) distribution.

6G networks: An introduction and a context-aware caching scheme for edge networks

Popularity matrix

• We extend the popularity function P such that:

P: Users × Item × Context → Ratings

• Hence, the popularity matrix is a function of not only users and items, but also the context in which user issued the request for the particular item.

6G networks: An introduction and a context-aware caching scheme for edge networks

Contextual attributes

• Six contextual information has been identified based on Schmidt et al. : information about user, social information, user’s tasks, location, infrastructure and physical conditions.
• The contextual information can be obtained from various sources such as sensors and logs.
• The popularity matrix is indexed according to a user, item and the specific context in which a data / video item is requested.

6G networks: An introduction and a context-aware caching scheme for edge networks

Tensor factorization

• Using tensor factorization, a low rank version of popularity matrix is constructed as shown in Figure.
• The tensor factorization decomposes the popularity matrix into factors of users, items and context inferred from popularity.
• There are a number of tensor factorization techniques available. We recommend the technique proposed by Karatzoglou et al. [6]

6G networks: An introduction and a context-aware caching scheme for edge networks

6G networks: An introduction and a context-aware caching scheme for edge networks

Gradient descent optimization

• The resultant factors are reduced to lower dimension k. Following least square problem is then solved to optimize the estimated popularity matrix:

​

6G networks: An introduction and a context-aware caching scheme for edge networks

Performing caching

• The resultant popularity matrix can be used for deciding the items to be cached proactively.
• The most popular files are greedily cached until there is not enough storage available.
• This helps in offloading the network during peak hours as most of the requests are satisfied from the cache.

6G networks: An introduction and a context-aware caching scheme for edge networks

Conclusion

• In this work, an overview of 6g technology is provided
• AI is going to play a very important role in 6g networks
• Work on novel communication spectrum, modulation techniques, intelligent radios are required
• Finally, an approach for caching at the edge is presented

6G networks: An introduction and a context-aware caching scheme for edge networks

Projects

• ALADIN: A data management framework for mobile ad hoc network
• TODE: Tool for ontology development and editing
• Load balancing in cloud / edge computing

6G networks: An introduction and a context-aware caching scheme for edge networks

References

[1] Yang, H., Alphones, A., Xiong, Z., Niyato, D., Zhao, J. and Wu, K., 2020. Artificial-intelligence-enabled intelligent 6G networks. IEEE Network, 34(6), pp.272-280.

[2] You, X., Wang, C.X., Huang, J., Gao, X., Zhang, Z., Wang, M., Huang, Y., Zhang, C., Jiang, Y., Wang, J. and Zhu, M., 2021. Towards 6G wireless communication networks: Vision, enabling technologies, and new paradigm shifts. Science China Information Sciences, 64(1), pp.1-74.

6G networks: An introduction and a context-aware caching scheme for edge networks

[3] Tomkos, I., Klonidis, D., Pikasis, E. and Theodoridis, S., 2020. Toward the 6G network era: Opportunities and challenges. IT Professional, 22(1), pp.34-38.

[4] Giordani, M., Polese, M., Mezzavilla, M., Rangan, S. and Zorzi, M., 2020. Toward 6G networks: Use cases and technologies. IEEE Communications Magazine, 58(3), pp.55-61.

6G networks: An introduction and a context-aware caching scheme for edge networks

[5] E. Bastug, M. Bennis, and M. r. Debbah, "Living on the edge: The role of proactive caching in 5G wireless networks," IEEE Communications Magazine, vol. 52, pp. 82-89, 2014.

[6] A. Karatzoglou, X. Amatriain, L. Baltrunas, and N. Oliver, "Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering," presented at Proceedings of the fourth ACM conference on Recommender systems, 2010.

6G networks: An introduction and a context-aware caching scheme for edge networks

Toward 6G Networks: Use Cases and Technologies

• https://www.youtube.com/watch?v=2npTuUHi78w

6G networks: An introduction and a context-aware caching scheme for edge networks