Led by European telecommunications operators, the so-called HEXA-X Consortium studies solutions for advanced 5th and 6th generation mobile networks. Through investments in carrier research and development, public-private partnerships, industry activities, and academic studies, HEXA-X tackles some of the toughest problems before structuring the powerful future networks. 6G communications on the continent. So far, the group’s research underscores the expected important contribution that artificial intelligence and machine learning will have for 6G networks by serving a plethora of functions in many layers of the network, such as spectral efficiency, network protocols and performance.
“Artificial intelligence and machine learning techniques, particularly deep learning, have advanced rapidly over the past decade, evolving in several areas including image classification, computer vision, and mapping. network,” says Mikko Uusitalo, research manager at Nokia Bell Labs, Radio Systems. Research Finland, and project leader and coordinator of HEXA-X. “And we expect these technologies to be introduced in many parts of the network at many layers and in many functions, from beamforming optimization at the radial layer, to distribution at the cell site and self-optimizing networks.
Artificial intelligence and machine learning will deliver better performance at a higher level of complexity and make the network inherently more energy efficient, consuming less energy to send the same amount of information. 6G can achieve this by changing the way the network encodes data.
The consortium is leveraging its “strong participation” from its 25 European members to help grow this 6G network foundation, as well as contributing to industry consensus around 5G and 6G protocols, Uusitalo shares. Nokia leads the consortium, which also includes Ericsson, Telecom Italia, Telefonica Spain, Siemens, Intel, Orange, WINGS ICT Solutions and other companies, organizations and universities. The group is also supported by the European Commission.
“HEXA-X creates a shared 6G vision and defines technology enablers for connectivity in three worlds, connecting the human, physical and digital worlds,” says Uusitalo. “Our goal is to lay the foundations for 6G, by structuring, framing and developing the connectivity technology by 2030.”
The consortium aligns with European priorities, taking into account the impact of digitization efforts in various industrial sectors on society, including sustainability issues, job creation and technological transformation in Europe. HEXA-X also links its work to the United Nations 2030 Agenda for Sustainable Development.
“We are looking at the significant challenges ahead of us, examining how we can and how we should contribute, even to such major challenges as climate change, the pandemic, the digital divide and social inequalities,” notes Uusitalo. “For example, we’re looking at the kind of opportunity we have with innovation to drive employment. We know that while technology is central to the digital economy, we need to reflect the complex needs of our society and seize the opportunity to deliver applicable digital solutions. We are a European project, so we do all this from a European perspective and to build European know-how. »
A two and a half year effort, HEXA-X has been running for about a year. The group began by articulating its vision, researching technologies, and developing use cases, and since then it has continued to define research challenges, find knowledge and technology gaps” and identify where we want to be,” he said.
One technology gap HEXA-X members are investigating is how to enable machine learning and artificial intelligence-based air interface design for a 6G network. To determine how to facilitate connected intelligence and governance of future networks, members are investigating different options for the structure of the air interface, or access mode, which is the communication link between two network stations in environments mobile and wireless (over the air) and involves both physical and data link layers.
Here, the consortium examines several novel data-driven transceiver design approaches, including cellless/device-to-device architectures, reconfigurable intelligent system-assisted architectures, and cellular architectures to support a complex 6G network. . For these architectures, the group is investigating how multiple system enablers—mobility management, resource allocation and link adaptation, and interference management—could help machine learning and artificial intelligence-based systems in the network. At the data link level, areas to consider include beamforming design, hardware degradation compensation, adaptive channel estimation, and data-driven channel decoding.
Additionally, Hexa-X members are laying the groundwork for new radio access technologies that operate at higher frequencies and perform high-resolution location and sensing that will work with a 6G environment. They are also considering network disaggregation and dynamic reliability capabilities.
Members have already published several key technical reports, including last summer’s AI-Driven Communication & Computation Co-Design. In the study, HEXA-X members explored ways to develop artificial intelligence (AI) as part of 6G networks; the role of data, including data quality, quantity, availability, ownership and monetization; confidentiality, security and integrity of data on the network; 6G use cases, their connected performance and value indicators; and applications to air interface and networked machine learning methods, among other topics.
A different report, “Novel Radio Access Technologies Towards 6G”, analyzed and modeled radio systems, important radio parameters, signal waveforms, radio deficiencies, modulation and beamforming and radio channels, all to prepare a 6G simulation framework with input parameters. Another study, “6G High-Resolution Localization and Sensing”, presented the first results of localization and mapping methods, signals and protocols, as well as insight into the accuracy of localization and sensing information that would allow other applications and communications.
Uusitalo expects the group to release “many more” technical studies, culminating in final reports on 6G network architectural enablers and technology solutions, and evaluation of network management and orchestration mechanisms. services. “Artificial intelligence can learn better 6G protocols, so we can use it to learn more optimal methods of accessing this shared radio spectrum,” he notes. “6G networks can be tailor-made for sustainability. And by designing 6G around AI/ML [machine learning], we can reduce the transmission power on 5G by up to 50% for the same bandwidth and data rates. We can build the network from scratch around this AI/ML, resulting in an AI-native air interface, increasing network efficiency while allowing many, many other devices to connect to it .
A member of the HEXA-X industry, WINGS ICT Solutions, based in Athens, Greece, is investigating the possibilities of such device connection for unmanned aerial systems and robotic applications in a 6G environment, says Panagiotis Demestichas, CEO and co-founder of the company. Demestichas, who is also a professor and researcher at the Department of Digital Systems at the University of Piraeus in Greece, HEXA-X’s academic partner, was the technical writer of the report “AI-Driven Communication & Computation Co-Design”.
“We are already seeing a difference in 5G, bringing a lot more robotics into the picture,” notes Demestichas. “There is still a lot of work to do around the cooperative robotics aspects, but with robotics in the 6G infrastructure, it will bring the [union] between the physical, digital, system and human worlds. We believe in this part of matching, matching the human worlds with the digital world and the mixture of intelligence, human intelligence and machines, with machines doing a lot more of the mundane things hopefully, but the machine and the human intelligence being always there. Another area we see with 6G is flexible topology. Some call it 3D, because the networks can come from the air, from the satellites to the air, to the terrestrial or submarine layer.
AI and ML designed into the infrastructure of a 6G network, into its air interface, will be a huge capability, he adds. “Artificial intelligence and machine learning functionality in the different layers or parts of the air interface [of a 6G network will allow] to learn from situations in order to predict situations and configure the air interface with a certain robustness, a certain certainty that you are doing the right thing”, explains the professor.
Over the next year, Demestichas and his HEXA-X team will work to advance a robotic application prototype for 6G. “We developed this collaborative robotic system, and then we will try to make the system self-configure on a 6G network, which includes a resilience part,” he shares. “We want to move from the lab environment to larger scale production, but to have larger production, we will work on the flexible topology. It may seem easy, but there are networking issues with a flexible topology and there are issues with the location of the feature, deciding whether it will be near a certain area or whether it will be somewhere else.
Since AI will be an integral part of 6G networks, WINGS is also focusing on how to govern AI. “Let’s say you have a lot of AI from applications running in your 6G network infrastructure,” he considers. “How do you ensure that everything goes well? How do you ensure the AI is doing what it should? So that’s an area we’re looking at. It is important to trust the system and to integrate this intelligence into the picture.
Finally, the team examines how advanced robotics, collaborative technologies, flexible network topologies, and AI governance can help achieve environmental sustainability.
For more information, visit hexa.x.eu.