Periodic Reporting for period 1 - DETERMINISTIC6G (DETERMINISTIC E2E COMMUNICATION WITH 6G)
Reporting period: 2023-01-01 to 2023-12-31
The ongoing digital transformation is rapidly reshaping industries and society, ushering in applications with unique communication and computational demands. From smart manufacturing and Extended Reality (XR) to wearable exoskeletons, this digital evolution is steering us towards a Cyber-Physical Continuum. In this realm, dependable, time-critical communications are vital for bridging the digital and physical worlds. The advent of 6G networks presents an unparalleled opportunity to lay the groundwork for an infrastructure that meets the exhaustive demands of these varied applications across multiple computational and communicative domains.
However, the diverse nature of current communication and computing technologies introduces significant challenges in creating a cohesive digital infrastructure; the handling of deterministic versus stochastic performance, is inadequately addressed by current integration approaches in 5G/5G-Advanced.
In this context, DETERMINISTIC6G emerges as a pioneering initiative aimed at defining the architecture and conceptual paradigms of 6G networks. It seeks to establish time-critical services for an integrated 6G ecosystem, focusing on dependability characteristics through visionary 6G use cases. The project is set to enhance 6G capabilities through innovative solutions for packet delay correction, AI/ML-driven latency characterization, and resource allocation strategies to mitigate the stochastic characteristics of 6G systems. A significant goal is to focus on the wireless-friendly enhancements of legacy deterministic communications (IEEE TSN, IETF DetNet), making them compatible with 6G's wireless nature. Further project focus areas are edge computing services, security framework, and the digital twinning of the 6G system in order to cover all relevant aspects of end-to-end (E2E) dependable communication.
Beyond conceptual developments, DETERMINISTIC6G aim to develop a simulation framework to validate proposed solutions across various deployment scenarios, ensuring the proposed concepts are robust and adaptable.
However, the diverse nature of current communication and computing technologies introduces significant challenges in creating a cohesive digital infrastructure; the handling of deterministic versus stochastic performance, is inadequately addressed by current integration approaches in 5G/5G-Advanced.
In this context, DETERMINISTIC6G emerges as a pioneering initiative aimed at defining the architecture and conceptual paradigms of 6G networks. It seeks to establish time-critical services for an integrated 6G ecosystem, focusing on dependability characteristics through visionary 6G use cases. The project is set to enhance 6G capabilities through innovative solutions for packet delay correction, AI/ML-driven latency characterization, and resource allocation strategies to mitigate the stochastic characteristics of 6G systems. A significant goal is to focus on the wireless-friendly enhancements of legacy deterministic communications (IEEE TSN, IETF DetNet), making them compatible with 6G's wireless nature. Further project focus areas are edge computing services, security framework, and the digital twinning of the 6G system in order to cover all relevant aspects of end-to-end (E2E) dependable communication.
Beyond conceptual developments, DETERMINISTIC6G aim to develop a simulation framework to validate proposed solutions across various deployment scenarios, ensuring the proposed concepts are robust and adaptable.
At the outset, the project's focus has been on exploring cutting-edge use cases. Therefore fully immersive Extended Reality (XR), industrial exoskeletons, adaptive manufacturing, and smart farming were meticulously selected due to their stringent demands for time-critical communication systems. The in-depth analysis of these use cases extends beyond the examination of Key Performance Indicators (KPIs)—like packet delay and its variations—to include Key Value Indicators (KVIs), covering socio-economic benefits and environmental sustainability, ensuring the 6G development is in harmony with wider societal and ecological goals. Investigations are ongoing into the architectural strategies and principles, aiming to construct a comprehensive end-to-end (E2E) architecture for reliable, time-critical services via 6G.
In advancing 6G system capabilities, an examination of packet delay and variation investigation highlighted a considerable discrepancy in Packet Delay Variation (PDV) between existing 5G/5G-Advanced systems and wired Time-Sensitive Networking (TSN) bridges. To bridge this gap, DETERMINISTIC6G introduced three innovative Packet Delay Correction (PDC) mechanisms designed to adjust the latency of packets within forthcoming 6G networks.
The project employed advanced data-driven approaches for latency characterization. Notably, Gaussian Mixture Models (GMMs) were augmented with extreme-value theory to accurately depict both bulk and tail regions of latency distributions, which is pivotal for underpinning time-sensitive communications. The efficacy of Machine Learning-based (ML) latency predictors was validated using data from commercial off-the-shelf (COTS) 5G networks and OpenAirInterface (OAI) platforms.
The project also explored various time synchronization architectures tailored for wired-wireless converged 6G networks. These models introduce redundancy in clock sources to enhance resilience. Additionally, in the security dimensions of time synchronization potential vulnerabilities were identified, and mitigation strategies were formulated.
In the realm of 6G-enabled, converged deterministic communication systems, the project concentrated on identifying and developing the key enablers for seamless end-to-end integration across time-critical communication technologies (such as 6G, Time-Sensitive Networking (TSN), and Deterministic Networking (DetNet)) and computational technologies (like edge cloud computing). The project has pinpointed existing gaps within various standardization efforts related to both wired and wireless dependable communications, setting the stage for potential advancements. Furthermore, a pioneering approach has been devised aimed at facilitating wireless-friendly E2E scheduling, which is designed to enhance the robustness of time-driven scheduling in wireless systems. This initiative serves as a crucial stepping stone in the transition from traditional TSN scheduling to a more stochastic regime. To address the integration with edge computing, a traffic-handling framework has been proposed to ensure seamless coordination between the traffic schedules of cloudified applications and communication networks.
DETERMINISTIC6G has achieved notable strides in concept validation: The simulation framework has been enhanced a data-driven model of 6G DetCom nodes, grounded in actual measurements. Additionally, a latency measurement framework was devised and implemented within an OpenAirInterface-based 5G system, facilitating granular latency analyses. The project's advancements also include the validation of a wireless-friendly approach to end-to-end scheduling for IEEE 802.1Qbv (scheduled traffic).
In advancing 6G system capabilities, an examination of packet delay and variation investigation highlighted a considerable discrepancy in Packet Delay Variation (PDV) between existing 5G/5G-Advanced systems and wired Time-Sensitive Networking (TSN) bridges. To bridge this gap, DETERMINISTIC6G introduced three innovative Packet Delay Correction (PDC) mechanisms designed to adjust the latency of packets within forthcoming 6G networks.
The project employed advanced data-driven approaches for latency characterization. Notably, Gaussian Mixture Models (GMMs) were augmented with extreme-value theory to accurately depict both bulk and tail regions of latency distributions, which is pivotal for underpinning time-sensitive communications. The efficacy of Machine Learning-based (ML) latency predictors was validated using data from commercial off-the-shelf (COTS) 5G networks and OpenAirInterface (OAI) platforms.
The project also explored various time synchronization architectures tailored for wired-wireless converged 6G networks. These models introduce redundancy in clock sources to enhance resilience. Additionally, in the security dimensions of time synchronization potential vulnerabilities were identified, and mitigation strategies were formulated.
In the realm of 6G-enabled, converged deterministic communication systems, the project concentrated on identifying and developing the key enablers for seamless end-to-end integration across time-critical communication technologies (such as 6G, Time-Sensitive Networking (TSN), and Deterministic Networking (DetNet)) and computational technologies (like edge cloud computing). The project has pinpointed existing gaps within various standardization efforts related to both wired and wireless dependable communications, setting the stage for potential advancements. Furthermore, a pioneering approach has been devised aimed at facilitating wireless-friendly E2E scheduling, which is designed to enhance the robustness of time-driven scheduling in wireless systems. This initiative serves as a crucial stepping stone in the transition from traditional TSN scheduling to a more stochastic regime. To address the integration with edge computing, a traffic-handling framework has been proposed to ensure seamless coordination between the traffic schedules of cloudified applications and communication networks.
DETERMINISTIC6G has achieved notable strides in concept validation: The simulation framework has been enhanced a data-driven model of 6G DetCom nodes, grounded in actual measurements. Additionally, a latency measurement framework was devised and implemented within an OpenAirInterface-based 5G system, facilitating granular latency analyses. The project's advancements also include the validation of a wireless-friendly approach to end-to-end scheduling for IEEE 802.1Qbv (scheduled traffic).
The DETERMINISTIC6G project is pioneering innovations by tackling three broad technical challenges: (i) architectural aspects for enhanced E2E dependable, time-critical communications; (ii) awareness for providing E2E deterministic performance; and (iii) improving anticipation for the assurance and control of performance guarantees.
In addressing the first challenge, DETERMINISTIC6G has laid down guiding principles for 6G architecture, including the seamless integration with edge computing and establishing end-to-end security frameworks.
A standout achievement is the development of advanced PDC mechanisms designed to mitigate Packet Delay Variation within future 6G networks—marking a significant advancement over current 5G technologies. Additionally, sophisticated latency prediction models using Mixture Density Networks (MDNs), enhanced with extreme-value theory, have been introduced for predicting real wireless network latencies. The exploration of resilient time synchronization architectures further underscores the project’s commitment to enhancing end-to-end time awareness.
A pivotal result is the creation of preliminary wireless-friendly end-to-end scheduling algorithms. These are adept at handling PDV in wireless environments, a dynamic distinctly challenging for traditional wired Time-Sensitive Networking (TSN) scheduling methods.
Regarding service assurance, the project has outlined fundamental principles for dependable communication and control. These include precise time-critical service specifications, monitoring and forecasting of communication and compute capabilities, maintaining service delivery status, and providing necessary feedback to applications.
In addressing the first challenge, DETERMINISTIC6G has laid down guiding principles for 6G architecture, including the seamless integration with edge computing and establishing end-to-end security frameworks.
A standout achievement is the development of advanced PDC mechanisms designed to mitigate Packet Delay Variation within future 6G networks—marking a significant advancement over current 5G technologies. Additionally, sophisticated latency prediction models using Mixture Density Networks (MDNs), enhanced with extreme-value theory, have been introduced for predicting real wireless network latencies. The exploration of resilient time synchronization architectures further underscores the project’s commitment to enhancing end-to-end time awareness.
A pivotal result is the creation of preliminary wireless-friendly end-to-end scheduling algorithms. These are adept at handling PDV in wireless environments, a dynamic distinctly challenging for traditional wired Time-Sensitive Networking (TSN) scheduling methods.
Regarding service assurance, the project has outlined fundamental principles for dependable communication and control. These include precise time-critical service specifications, monitoring and forecasting of communication and compute capabilities, maintaining service delivery status, and providing necessary feedback to applications.