Federated-Learning-Enabled Intelligent Fog Radio Access Networks: Fundamental Theory, Key Techniques, and Future Trends

Zhao, Zhongyuan; Feng, Chenyuan; Yang, Howard H.; Luo, Xueting

doi:10.1109/mwc.001.1900370

Cited by 110 publications

(43 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Determine EE-optimal and SE-optimal resource allocations, denoted by, (P SE , Q SE , a SE , b SE ) and (P EE , Q EE , a EE , b EE ), respectively, by using Algorithm 1 and Algorithm 2. 2: Initialize: (1)…”

Section: A Near-optimal Algorithm Designmentioning

confidence: 99%

“…Accordingly, by taking linear combination of the two consecutive points of F, we obtain F (1) as a new set of weakly Pareto optimal solutions to P0 where |F (1) | − |F| = N F − 1. In this way, the set of achievable weakly Pareto optimal solutions can be evolved as F → F (1) → F (2) → • • • → F (f inal) . In the aforementioned sequence, the number of weakly Pareto optimal solutions is increased at each evolution.…”

Section: Appendix Gmentioning

confidence: 99%

“…Leveraging centralized cloud processing based resource allocation, distributed signal processing, and popular content caching at the network edge, fog-radio access network (F-RAN) presents a revolutionary paradigm to satisfy the beyond 5G (B5G) performance requirements [1]. In edgecaching (EC) enabled F-RAN, the content distribution phase is significantly important to ensure throughput and diverse latency requirements of the user devices (UDs).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Hassan¹

2021

Preprint

View full text Add to dashboard Cite

<div>Multi-objective resource allocation is studied for edge-caching enabled fog-radio access network. Notably, joint maximization of the energy-efficiency (EE) and spectrum-efficiency (SE) and interference management are investigated for distributing contents from the cache-enabled fog access points (F-APs) and cloud base station (CBS) to the user devices (UDs). In our envisioned system, the UDs are grouped into multiple non-overlapping device-clusters based on their locations. A rate-splitting with common message decoding based transmission strategy is applied to enable UDs of each device-cluster to receive data from a suitably selected F-AP and CBS over the same radio resource blocks. To maximize system EE and SE jointly, a multi-objective optimization problem (MOOP) is formulated and it is solved in three stages. At first, by employing the $\epsilon$-constraint method, the MOOP is converted to an EE-SE trade-off optimization problem. Then, by leveraging iterative function evaluation based power control and generalized 3D-resource matching, the EE-SE trade-off optimization problem is solved and a novel resource allocation algorithm is proposed to obtain near-optimal Pareto-front for the proposed MOOP. To reduce the complexity of obtaining near-optimal Pareto-front, a sub-optimal resource allocation algorithm is proposed as well. Finally, a low-complexity algorithm is devised to select a suitable operating EE-SE pair from the obtained Pareto-front. The conducted simulations demonstrate that the proposed resource allocation schemes achieve substantial improvement of system EE and SE over the benchmark schemes. </div>

show abstract

Section: A Near-optimal Algorithm Designmentioning

confidence: 99%

Section: Appendix Gmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Hassan¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The deep reinforcement learning has also been applied to realize network slicing in F-RAN in [17], where computing, caching and radio resources are orchestrated to meet the performance requirements of two different types of services: hot-spot and vehicle-to-infrastructure (V2I). To address the challenges of high cost of data offloading and model training for implementing network intelligence at the edge, an evolved architecture of F-RAN is proposed in [18], which employs federated learning (a.k.a. collaborative learning) to realize intelligent signal processing and network management with less communication overhead and greater efficiency than existing centralized learning paradigms.…”

Section: Related Workmentioning

confidence: 99%

Performance Analysis of Opportunistic Fog Based Radio Access Networks

2020

View full text Add to dashboard Cite

“…Leveraging distributed signal processing, resource allocation, and popular content caching at the network edge, fog-radio access network (F-RAN) presents a revolutionary paradigm to alleviate burden over fronthaul network in the beyond 5G architecture [1]. In a multi-level edgecaching (EC) enabled system, the content distribution phase is significantly important to ensure throughput and diverse latency requirements of the end-users.…”

Section: Introductionmentioning

confidence: 99%

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Hassan

Hossain

Cheng

et al. 2021

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Multi-objective resource allocations are studied for a multi-level edge-caching enabled fog-radio access network. Notably, joint maximization of the energy-efficiency (EE) and spectrum-efficiency (EE) and interference management for the content distribution phase are investigated. In the envisioned system, the popular contents are cached at both the fog access point (F-AP) and fog user equipments (F-UEs), and the content-requesting devices are grouped into multiple device-clusters based on their locations. Using a rate-splitting with common message decoding based transmission strategy, each device-cluster is simultaneously served by a suitably selected F-UE and the F-AP over the same radio resource blocks. To maximize system EE and SE of the content distribution phase jointly, a multi-objective optimization problem (MOOP) is formulated. By using the-constraint method, the proposed MOOP is converted to an EE-SE trade-off optimization problem. Leveraging iterative function evaluation based power control and generalized 3D-resource matching, a novel algorithm is devised to obtain near-optimal Pareto front for the proposed MOOP. By inspecting solutions over the Pareto optimal front, a suitable operating EE-SE pair and the corresponding resource allocation variables are obtained. A low-complexity algorithm to obtain a suitable EE-SE trade-off is also devised. The conducted simulations confirm that the proposed algorithms achieve substantial improvement of system EE and SE over the baseline schemes.

show abstract

Federated-Learning-Enabled Intelligent Fog Radio Access Networks: Fundamental Theory, Key Techniques, and Future Trends

Cited by 110 publications

References 9 publications

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Performance Analysis of Opportunistic Fog Based Radio Access Networks

Energy-Spectrum Efficient Content Distribution in Fog-RAN Using Rate-Splitting, Common Message Decoding, and 3D-Resource Matching

Contact Info

Product

Resources

About