“…Moreover, the fog computing paradigm introduced above for industrial IoT poses the challenge of placing the processing functions on the continuum from devices to the cloud. Such placement can be optimized for minimizing energy consumption while ensuring performance [14], and the fog function placement may be integrated within the global 6G O-RAN architecture.…”
Sustainability and energy sobriety should guide the "why" and the "how" of 6G. It is mandatory that the 6G infrastructure and services have a very low environmental footprint, but also, and more importantly, the 6G technology should be designed on the 5G basis for enabling added-value services for the society and to mitigate the environment footprint. This paper presents a vision for 6G network as an enabler for a more sustainable society, e.g. by enabling the society of maintenance and care and fostering innovation in the industry. On the other hand, some technology enablers for an energy sober 6G network are presented, along with guidelines for network deployments and for the assessment of the global impact of 6G services.
“…Moreover, the fog computing paradigm introduced above for industrial IoT poses the challenge of placing the processing functions on the continuum from devices to the cloud. Such placement can be optimized for minimizing energy consumption while ensuring performance [14], and the fog function placement may be integrated within the global 6G O-RAN architecture.…”
Sustainability and energy sobriety should guide the "why" and the "how" of 6G. It is mandatory that the 6G infrastructure and services have a very low environmental footprint, but also, and more importantly, the 6G technology should be designed on the 5G basis for enabling added-value services for the society and to mitigate the environment footprint. This paper presents a vision for 6G network as an enabler for a more sustainable society, e.g. by enabling the society of maintenance and care and fostering innovation in the industry. On the other hand, some technology enablers for an energy sober 6G network are presented, along with guidelines for network deployments and for the assessment of the global impact of 6G services.
“…In our paper, we propose to investigate machine learning techniques based on Reinforcement Learning to reach near optimal solutions of the virtualized face detection optimization problem in edge infrastructures. Our objective is to train RL models to improve the quality of the solutions compared to the results of the first paper addressing this problem (see reference [8]).…”
Section: Related Workmentioning
confidence: 99%
“…The addressed problem of virtualized face detection optimization and mapping is NP-Complete. More details on the proof can be found in [8].…”
Section: Problem Complexitymentioning
confidence: 99%
“…Constraints (8) guarantee that each virtual arc pi, i `1q is deployed on exactly one physical path. `ypi,i`1qpj1,j2,kq `ypi,i`1qpj2,j1,kq ˘bpi,i`1q ď min j1j2k @l P t1, 2, 3u, @j 1 P V , @j 2 P Ppj 1 , lq, @k P K pj 1 , j 2 , lq…”
Section: Integer Linear Programming (Exact) Approachmentioning
Real-time requirements in video streaming and processing are increasing and represent one of the major issues in industry 4.0 domains. In particular, Face Detection (FD) use-case has attracted the interest of industrial and academia researchers for various applications such as cyber-physical security, fault detection, predictive maintenance, etc. To ensure applications with real time performance, Edge Computing is a good approach which consists in bringing resources and intelligence closer to connected devices and hence, it can be used to cope with strong latency and throughput expectations. In this paper, we consider optimal routing, placement and scaling of virtualized face detection services at the edge. We propose an edge networking approach based on Integer Linear formulation to cope with small problem instances. A reinforcement learning solution is proposed to address larger problem sizes and scalability issues. We assess the performance of our proposed approaches through simulations and show advantages of the reinforcement learning approach to converge towards near-optimal solutions in negligible time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.