Periodic Reporting for period 1 - EXPLOR (EXperimentation and simulation based PLatform for beyond 5G Optical-wireless network Research and development)
Période du rapport: 2020-01-01 au 2021-12-31
The EXPLOR project aims to merge the disciplinary fields of optical and wireless communication and networking to develop an integrated and flexible networking software targeting beyond the 5G network scenario. EXPLOR research scenario considers small virtualized cell (i.e. femto-cell) deployments, and the extended concepts of C-RAN, optical fronthaul (OFH), and technology coexistence. EXPLOR project objective is to develop integrated software solutions and explore the cost, complexity and performance implications of various technologies. As such, innovative aspects of the EXPLOR project will enable consideration of flexible, multi-tech OFH architectures supporting coexistence with legacy technologies, improved aggregate network capacity at lower cost, as well as enhancements in spectral, energy and area efficiency.
Several 5G and Optical transmission toolsets are being widely used for research, design and tutoring purposes, yet individually fragmented and subjected to limitations in terms of performance and cost. The interoperability between individual software toolsets is typically prohibitively limited. EXPLOR will counter those drawbacks.
EXPLOR project hinges on inter-sectoral collaboration and pronounced training and knowledge transfer between the multidisciplinary academic and industrial partners.
Several 5G and Optical transmission toolsets are being widely used for research, design and tutoring purposes, yet individually fragmented and subjected to limitations in terms of performance and cost. The interoperability between individual software toolsets is typically prohibitively limited. EXPLOR will counter those drawbacks.
EXPLOR project hinges on inter-sectoral collaboration and pronounced training and knowledge transfer between the multidisciplinary academic and industrial partners.
This periodic report covers phase 1 and a part of phase 2 of EXPLOR project implementation. During phase 1 we identified relevant use case scenarios and performance heuristics, providing interoperability, optimization, validation and business model considerations towards resource orchestration, femto-cell deployment, OFH design and network cognition within the project scenario. Successful conclusion of phase 1 marked the start of the second project phase, where the EXPLOR team has worked towards various aims of modeling extension. The development of dynamic functional split framework in coexistent 5G/B5G C-RAN environment includes an analytical modeling for admission ratio (AR) in network function virtualization (NFV)-based converged optical-wireless networks, the aim of which was enabling network dimensioning towards optimized capacity of all network elements, relevant for derivation of FS requirements placed on the OFH. We continue the development of virtualized functional blocks targeting efficient scheduling, whereby the above mentioned framework will be extended to incorporate mobility schemes. Towards SG modeling extension, we have completed surveys on non-homogeneous point process models and 2D scenarios, and commenced the development of SG models for 3D and mobility scenarios. Modeling of several candidates optical SDT components and their validation using SOTA collected datasets has also been completed, along with a review of impairment mitigation methods for the OFH architecture under EXPLOR scenario, and adoption of the artificial neural network (ANN) based approach. We have developed a modelling framework for ANN based signal equalization, enabling the currently ongoing testing of various architectures, training strategies, activation and loss functions, as well as high order signaling formats. On the system level, we adopted and implemented the exhaustive Gaussian detection approach with optimized threshold following the project phase 1 aims of pursuing the most computationally efficient yet generalized approach in architecture assessments. Towards the development of virtualization algorithm precursors, we are developing an efficient impairment aware tool based on closed-form expressions, including functionalities primarily targeting low computational latency towards its effective integration with ML optimization in the following project phases. So far, our dissemination activities have resulted in a number of scientific publications, including journal, conference (available on Zenodo) and book chapter publications, whereas several journal publications are currently either in review stage or in the final stages of preparation for submission.
In NG virtualized networks, VNFs interconnected via a set of virtual links (vLinks) comprise service function chains (SFCs) towards delivering specific services to the end users. This process greatly affects the network techno-economy as VNFs consume computational resources of the network's servers, while vLinks rely on network transmission resources. EXPLOR goes beyond the SOTA challenge of efficient resource utilization by proposing a novel analytical framework for the AR calculation in NFV-based converged optical-wireless 5G networks, employing a network slicing architecture. We take into account the occupancy distribution in both network computational (servers) and transmission (OFH fiber links) domains, as well as the SFC establishment AR by taking into account different sub-service-classes belonging to different slices. The modeling accuracy is validated via the comparison of analytical and simulation results. The proposed model is employed for the determination of the optimal (minimum) capacity for all SFCs elements (VNFs and vLinks). We also highlight that the framework boasts minimized computational complexity by relying on recursive formulas as opposed to computationally inefficient SOTA simulations, and mitigates the application of complex optimization algorithms.
In our SG modeling segment, we first present the predominant multi-tier network model of independent Poisson point processes (PPPs) utilizing multiple spectrum bands, along with an example use case for using the clustered point processes for modeling distances and proximity in mobile data networks. We further provide a review of existing approaches relevant to MMW femtocell operation in the context of THz communications. Our current activities beyond SOTA target the extension of our approach towards 3D modeling using Poisson cluster process (PCP) and the inclusion of mobility (RWP), with the particular focus on the angle estimation, beam management and handover decisions.
Our beyond SOTA activities on OFH and ML based optimization modeling currently focus on the development of OFH frameworks tailored for successful integration of neural network based ML optimization methods, as well as the system level mitigation of main transmission impairments in EXPLOR scenario. We have developed an integrated modelling framework for the application of ANN based signal equalization, enabling current research targeting beyond SOTA architecture optimization The mitigation of transmission impairments in the optical segment of EXPLOR scenario requires signal processing that can effectively adapt to varying transmission conditions imposed on continuous streams of data. We are thus currently pursuing the application of novel learning approaches in deep neural networks (DNN) for linear and nonlinear equalization in long haul transmission systems. This work investigates and proposes a novel DNN architecture to overcome a problem of catastrophic forgetting in deep neural networks that can be used for the mitigation of critical impairments in EXPLOR scenario. We perform comparisons against a number of SOTA methods and traditional DNN implementations and demonstrate improvements in training accuracy towards signal recovery and increased flexibility. The results, which are currently under a journal publication peer review, show that the method may be successfully used towards the increase in transmission reach.
In our SG modeling segment, we first present the predominant multi-tier network model of independent Poisson point processes (PPPs) utilizing multiple spectrum bands, along with an example use case for using the clustered point processes for modeling distances and proximity in mobile data networks. We further provide a review of existing approaches relevant to MMW femtocell operation in the context of THz communications. Our current activities beyond SOTA target the extension of our approach towards 3D modeling using Poisson cluster process (PCP) and the inclusion of mobility (RWP), with the particular focus on the angle estimation, beam management and handover decisions.
Our beyond SOTA activities on OFH and ML based optimization modeling currently focus on the development of OFH frameworks tailored for successful integration of neural network based ML optimization methods, as well as the system level mitigation of main transmission impairments in EXPLOR scenario. We have developed an integrated modelling framework for the application of ANN based signal equalization, enabling current research targeting beyond SOTA architecture optimization The mitigation of transmission impairments in the optical segment of EXPLOR scenario requires signal processing that can effectively adapt to varying transmission conditions imposed on continuous streams of data. We are thus currently pursuing the application of novel learning approaches in deep neural networks (DNN) for linear and nonlinear equalization in long haul transmission systems. This work investigates and proposes a novel DNN architecture to overcome a problem of catastrophic forgetting in deep neural networks that can be used for the mitigation of critical impairments in EXPLOR scenario. We perform comparisons against a number of SOTA methods and traditional DNN implementations and demonstrate improvements in training accuracy towards signal recovery and increased flexibility. The results, which are currently under a journal publication peer review, show that the method may be successfully used towards the increase in transmission reach.