Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach

Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach

12 Feb 2024 | Emilio Calvanese Strinati, Paolo Di Lorenzo, Vincenzo Sciancalepore, Adnan Aijaz, Marios Kountouris, Deniz Gündüz, Petar Popovski, Mohamed Sana, Photos A. Stavrou, Beatriz Soret, Nicola Cordeschi, Simone Scardapane, Mattia Merluzzi, Lanfranco Zanzi, Mauro Boldi Renato, Tony Quek, Nicola di Pietro, Olivier Forceville, Francesca Costanzo, Peizheng Li
The 6G-GOALS project aims to develop goal-oriented and semantic communication for AI-native 6G networks. This approach integrates communication, computation, control, and intelligence to optimize bandwidth, latency, energy, and electromagnetic field (EMF) radiation. The project focuses on distilling data to its most relevant form, aligning with the source's intent or the destination's objectives and context, or serving a specific goal. The three fundamental pillars of 6G-GOALS are: i) AI-enhanced semantic data representation, sensing, compression, and communication; ii) foundational AI reasoning and causal semantic data representation, contextual relevance, and value for goal-oriented effectiveness; and iii) sustainability enabled by more efficient wireless services. The project also illustrates two proof-of-concepts implementing semantic, goal-oriented, and pragmatic communication principles in near-future use cases. The 6G-GOALS system architecture is built on the O-RAN architecture, which is a key enabler of innovation in 6G. The essential design elements include establishing an AI-native 6G system specifically tailored for semantic and goal-oriented communications, offering a flexible design with intelligent network functions, implementing a semantic plane that enhances both the user plane and the control plane, and creating an intelligent and adaptable Radio Access Network (RAN) to effectively handle semantic and goal-oriented communication on a large scale. The key components of the system architecture include the semantic engine, semantic RIC, RAN semantic plane, application plane, UE and edge components, knowledge base, and enhanced core network. The semantic engine is responsible for the effective and efficient delivery of semantic-oriented services. The semantic RIC provides a programmable and extensible platform for the deployment of semantic-oriented applications. The RAN semantic plane spans the CU, the DU, and the RU. The application plane is orthogonal to the semantic plane and provides necessary interfaces for the semantic applications across edge devices or user equipment. The UE and edge components will be significantly upgraded with advanced computational and learning abilities. The knowledge base is a cornerstone of this architecture, seamlessly involved in virtually all aspects of semantic processing modules. The enhanced core network can further support the semantic-empowered functionalities of 6G-GOALS for the RAN and the management, orchestration, and application domains. The 6G-GOALS framework aims to go beyond the established limits of the current sense-compute-connect-control models and transition toward semantic communication-based AI architectures, protocols, and services. The envisioned pillars are described as (i) AI-empowered semantic data representation, sensing, compression, and communication; (ii) timing-aware semantic communication for distributed reasoning and actuation; (iii) 6G sustainability via semantic-empowered RAN. The project also explores new methodologies for semantic and goal-oriented communications, including semantic data acquisition, representation, and compression, semantic source and channel coding schemes, and timing-aware semantic communication for distributed reasoning and actuation. The projectThe 6G-GOALS project aims to develop goal-oriented and semantic communication for AI-native 6G networks. This approach integrates communication, computation, control, and intelligence to optimize bandwidth, latency, energy, and electromagnetic field (EMF) radiation. The project focuses on distilling data to its most relevant form, aligning with the source's intent or the destination's objectives and context, or serving a specific goal. The three fundamental pillars of 6G-GOALS are: i) AI-enhanced semantic data representation, sensing, compression, and communication; ii) foundational AI reasoning and causal semantic data representation, contextual relevance, and value for goal-oriented effectiveness; and iii) sustainability enabled by more efficient wireless services. The project also illustrates two proof-of-concepts implementing semantic, goal-oriented, and pragmatic communication principles in near-future use cases. The 6G-GOALS system architecture is built on the O-RAN architecture, which is a key enabler of innovation in 6G. The essential design elements include establishing an AI-native 6G system specifically tailored for semantic and goal-oriented communications, offering a flexible design with intelligent network functions, implementing a semantic plane that enhances both the user plane and the control plane, and creating an intelligent and adaptable Radio Access Network (RAN) to effectively handle semantic and goal-oriented communication on a large scale. The key components of the system architecture include the semantic engine, semantic RIC, RAN semantic plane, application plane, UE and edge components, knowledge base, and enhanced core network. The semantic engine is responsible for the effective and efficient delivery of semantic-oriented services. The semantic RIC provides a programmable and extensible platform for the deployment of semantic-oriented applications. The RAN semantic plane spans the CU, the DU, and the RU. The application plane is orthogonal to the semantic plane and provides necessary interfaces for the semantic applications across edge devices or user equipment. The UE and edge components will be significantly upgraded with advanced computational and learning abilities. The knowledge base is a cornerstone of this architecture, seamlessly involved in virtually all aspects of semantic processing modules. The enhanced core network can further support the semantic-empowered functionalities of 6G-GOALS for the RAN and the management, orchestration, and application domains. The 6G-GOALS framework aims to go beyond the established limits of the current sense-compute-connect-control models and transition toward semantic communication-based AI architectures, protocols, and services. The envisioned pillars are described as (i) AI-empowered semantic data representation, sensing, compression, and communication; (ii) timing-aware semantic communication for distributed reasoning and actuation; (iii) 6G sustainability via semantic-empowered RAN. The project also explores new methodologies for semantic and goal-oriented communications, including semantic data acquisition, representation, and compression, semantic source and channel coding schemes, and timing-aware semantic communication for distributed reasoning and actuation. The project
Reach us at info@study.space
[slides] Goal-Oriented and Semantic Communication in 6G AI-Native Networks%3A The 6G-GOALS Approach | StudySpace