Periodic Reporting for period 1 - BeGREEN (Beyond 5G Artificial Intelligence Assisted Energy Efficient Open Radio Access Network)
Période du rapport: 2023-01-01 au 2023-12-31
BeGREEN will take a holistic view of the radio access network to provide an evolved segment that not only accommodates increasing traffic and service levels but also considers power consumption as a factor. At a hardware level, techniques will include improvement of the energy efficiency of power amplifiers and the appropriate use of accelerators to reduce power consumption relative to the use of generic compute platforms when performing network function virtualisation. At the link level, techniques to provide a better estimate of the impact of the radio channel will be considered and the resulting improvement in spectral efficiency balanced against the increased power consumption associated with the resulting calculations. At a system level, new nodes and architectures are considered that move away from the assumption that additional capacity requires installation of new base-stations. These architectural considerations will include enhanced capabilities and components such as Reconfigurable Intelligent Surfaces (RIS) and cell-free architectures that could provide a better distribution of radio power around an area when compared to the centralised cellular approach. To achieve the expected hardware, link-level and system-level benefits, research into some fundamental capabilities are required. The use of AI/ML techniques provides a solution to reduce the number of calculations required when compared to a more traditional approach. AI/ML can also be used to recognise patterns in the system level data associated with the behaviour of the user base and to learn the most appropriate response to this behaviour in terms of both network performance and also energy consumption. The location at which these AI/ML operations are carried out within the network will also have an impact on the performance of the approach, the consumption of power and the ability to share resources between different operations. The movement of data around the network to the appropriate location for calculations to be carried out also requires the definitions of new interfaces and protocols to enable the data to be processed in an open architecture of virtualised network functions. For this reason, the project will assume that the emerging O-RAN standard and its evolution is the baseline architecture. The disaggregation, virtualisation and network and service management capabilities inherent in O-RAN provide the mechanisms to realise many of the above-mentioned infrastructure changes and techniques for energy optimisation.
Determining the metrics by which power consumption should be included is a key feature of the project, and the different mechanisms by which power consumption could be reduced will be evaluated. An obvious first stage will be to consider the cost of the energy but also societal factors, linked to the necessary reduction in global emissions will also be considered.
Determining the metrics by which power consumption should be included is a key feature of the project, and the different mechanisms by which power consumption could be reduced will be evaluated. An obvious first stage will be to consider the cost of the energy but also societal factors, linked to the necessary reduction in global emissions will also be considered.
The work performed so far has focused on the identification of energy-wise potential improvements among the RAN elements, leading to enhanced radio network deployments definitions.
The architectural design has been one of the main focus during Period 1, exploring optimization strategies, the way to supply of control mechanisms to be applied to the baseline (reference) architecture of the project, which is 3GPP and O-RAN. AI/ML-based improvements have been studied and their implementation mapped to the architectural design. For this, the design of the BeGREEN Intelligent Plane has been promoted in D4.1 including its main components and interfaces, and according to the requirements of the targeted use cases and energy efficient optimisations. Mapping of required components and control options for such components - mainly stemming from WP3. The Intelligent Plane has been mapped to the O-RAN architecture to analyse compliance and gaps, which could lead to extended and new components and/or interfaces (e.g. Relays, RIS and Edge infrastructure). Related to the Intelligent Plane, the design of the AI Engine architecture to support AI-driven energy efficient optimisations has been key in Period 1. This engine is based on serverless offloading and loosely coupled approaches, providing a framework to support AI/ML services.
At component level, WP3 has defined how the implementation of known 5G O-RAN components –particularly the CU and DU– can be realized in a different (and optimised) architecture, optionally offloading some of the functionalities to accelerators. The project is expecting a considerable improvement compared to the implementation in SotA architectures. Specifically for the RU and its energy efficiency improvements, work is being carried out both from the development of techniques for the optimization of the physical components of the RU and using the O-RAN capabilities, but also to leverage from the RICs to optimally manage the RU. The design and future implementation of the additional PHY components (and their optimisation) to improve energy efficiency and to reduce the energy consumption is pursued. Particular interest is put on the integration of external components to the 3GPP or O-RAN architectural framework - such as the use of ISAC and the employment of RIS and relays - that could allow providing a plethora of possibilities to improve the energy efficiency of the RAN. The envisioned initial design of these components and also other techniques for interference management in relay-enhanced scenarios have been studied in D3.1.
At the demonstration level, as part of Task 5.1 the different Proofs of Concept have been detailed in D5.1
The architectural design has been one of the main focus during Period 1, exploring optimization strategies, the way to supply of control mechanisms to be applied to the baseline (reference) architecture of the project, which is 3GPP and O-RAN. AI/ML-based improvements have been studied and their implementation mapped to the architectural design. For this, the design of the BeGREEN Intelligent Plane has been promoted in D4.1 including its main components and interfaces, and according to the requirements of the targeted use cases and energy efficient optimisations. Mapping of required components and control options for such components - mainly stemming from WP3. The Intelligent Plane has been mapped to the O-RAN architecture to analyse compliance and gaps, which could lead to extended and new components and/or interfaces (e.g. Relays, RIS and Edge infrastructure). Related to the Intelligent Plane, the design of the AI Engine architecture to support AI-driven energy efficient optimisations has been key in Period 1. This engine is based on serverless offloading and loosely coupled approaches, providing a framework to support AI/ML services.
At component level, WP3 has defined how the implementation of known 5G O-RAN components –particularly the CU and DU– can be realized in a different (and optimised) architecture, optionally offloading some of the functionalities to accelerators. The project is expecting a considerable improvement compared to the implementation in SotA architectures. Specifically for the RU and its energy efficiency improvements, work is being carried out both from the development of techniques for the optimization of the physical components of the RU and using the O-RAN capabilities, but also to leverage from the RICs to optimally manage the RU. The design and future implementation of the additional PHY components (and their optimisation) to improve energy efficiency and to reduce the energy consumption is pursued. Particular interest is put on the integration of external components to the 3GPP or O-RAN architectural framework - such as the use of ISAC and the employment of RIS and relays - that could allow providing a plethora of possibilities to improve the energy efficiency of the RAN. The envisioned initial design of these components and also other techniques for interference management in relay-enhanced scenarios have been studied in D3.1.
At the demonstration level, as part of Task 5.1 the different Proofs of Concept have been detailed in D5.1