# A Federated Learning-Based Resource Allocation Scheme for Relaying-Assisted Communications in Multicellular Next Generation Network Topologies

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Related Works

#### 1.2. Contributions and Paper’s Structure

- We first formulate the problem of optimal RN selection and subcarrier allocation for each user served by the cooperative relaying-assisted system, which serves users that cannot be served directly from BSs, either for path loss or power management purposes.
- For the aforementioned problem, a DL-based algorithm is proposed. The primary goal is to maximize EE and SE levels both for each cell and for the whole coverage area.
- In order to relax the network’s computation load, the training of this DL scheme is performed using an FL-based computation offloading framework, where different edge devices (either UEs with certain computation capabilities and/or MEC servers installed in the BSs) are assigned with the execution of a portion the training phase. Afterward, the local updates are aggregated to form a global model—hosted at the central BS of the topology—that concerns the total system’s EE and SE maximization. Local models (before aggregation) utilize data from the cells that are hosted and utilize a local mechanism for local EE and SE maximization.
- The performance of the proposed framework is evaluated by extensive system and link-level simulations in different usage scenarios utilizing a B5G system and link-level simulator extending the work performed in [48]. Results indicate that the proposed FL-based RN selection and resource allocation scheme can overperform state-of-the-art approaches (both non-ML and CL ones) in improving various key performance indicators (KPIs) of interest (EE and SE). Furthermore, the proposed decentralized ML training scheme achieves the required training time minimization, which is a crucial aspect in B5G/6G network orientations.
- To sum up, the utilization of the proposed FL scheme for efficient RN selection and RRM in each cell of the multicellular topology, which provides a fully data-driven automated decision-making mechanism for high-interference dense B5G/6G environments and optimizes both network and ML performance metrics (focusing on EE, SE, and ML algorithms’ training time), is the key novelty of this paper.

## 2. B5G Multicellular Orientation

#### 2.1. System Model for RN Selection in B5G/6G Cooperative Networks

- ${S}_{BS}=\{B{S}_{1},B{S}_{2},\dots ,B{S}_{M}\}$, where $M$ denotes the total number of Macro-BSs in the topology.
- ${S}_{RN}=\{{RN}_{1},{RN}_{2},\dots ,{RN}_{R}\}$, where $R$ denotes the total number of A&F RNs in the topology.
- ${S}_{UE}=\{{UE}_{1},{UE}_{2},\dots ,{UE}_{N}\}$, where $N$ denotes the total number of UEs that sequentially reach the topology.

- ${L}_{b,u}$, where $b\in {S}_{BS}$ and $u\in {S}_{UE}$, which denotes a BS-UE link.
- ${L}_{b,r}$, where $b\in {S}_{BS}$ and $r\in {S}_{RN}$, which denotes a BS-RN link.
- ${L}_{r,u}$, where $b\in {S}_{RN}$ and $u\in {S}_{UE}$, which denotes a RN-UE link.

^{th}UE ($1\le n\le N$) associated with the l

^{th}subcarrier ($1\le l\le {N}_{sc}$) assuming independent BS-RN and RN-UE links, as well as a specific channel realization, is given by [18]:

#### 2.2. Federated Learning Architecture

- (C1): $\sum _{s\u03f5{S}_{n}}{p}_{n,s}\le {p}_{m}$, where ${p}_{m}$ is the maximum power limit per UE.
- (C2): $\sum _{n\u03f5U{E}_{b}}\sum _{l\in {S}_{n}}{p}_{n,l}\le {P}_{m}$, where ${P}_{m}$ is the maximum power limit per BS and the set $U{E}_{b}$ consists of UE that are served by the ${b}^{th}$ BS.
- (C3): $SNI{R}_{n,l}\ge SNI{R}_{thr}$, where $SNI{R}_{thr}$ sets the minimum SNIR threshold for acceptable QoS and has different values based on the modulation level of each UE.
- (C4): $\sum _{n\in U{E}_{b}}\left|{S}_{n}\right|\le {N}_{sc}$, in order for all the BSs to have equal access to the available subcarriers.

## 3. Proposed Federated Learning Framework

#### 3.1. Dataset Construction

- UEs are not uniformly distrusted in the B5G/6G network’s coverage area.
- Algorithm 1 of [48] has been updated so that the best RN (out of the deployed ones in each cell) is selected based on the DRL scheme presented in [18]. Hence, the collaboration of m-MIMO and orthogonal frequency division multiple access (OFDMA) principles in RN-assisted multi-hop B5G cellular setups is integrated with contemporary ML techniques to optimize the overall system’s EE and SE levels.

- A feature input later with z-score normalization of the input, where ${D}_{size}$ features are inserted.
- A fully connected layer with 50 × 1 output size, where the input is multiplied (feature input layer) by the corresponding weight matrix; also, the bias vector is added.
- A batch normalization layer, to normalize data across all observations for each channel independently, making training of the NN faster through re-centering and re-scaling.
- A rectified linear unit (ReLU) layer, using a rectified activation function to force the input directly to the output if it is positive, otherwise, to zero output.

#### 3.2. FL for Training Optimization

Algorithm 1: FL-based RN selection and RRM algorithm for EE, SE maximization | ||||

1 | Input:$\mathrm{learning}\mathrm{rate}{\lambda}_{t}$$,\mathrm{number}\mathrm{of}\mathrm{BSs}M$$,\mathrm{number}\mathrm{of}\mathrm{UEs}N$$\mathrm{and}\mathrm{of}\mathrm{RNs}\mathrm{per}\mathrm{BS}{R}_{BS}$ | |||

2 | Initialization:$t=0,{w}_{0}^{r}=0$ | |||

3 | for$t=0$$\mathbf{t}\mathbf{o}t=T$ do | |||

BS Algorithm steps$(\forall m\in M$) | ||||

4 | Step 1—Model dissemination:$\mathrm{the}\mathrm{BS}\mathrm{broadcast}\mathrm{the}\mathrm{updated}\mathrm{global}\mathrm{model}{w}_{t}$$\mathrm{and}\mathrm{the}\mathrm{corresponding}\mathrm{learning}\mathrm{rate}{\lambda}_{t}$ to all edge devices located to RNs | |||

5 | Step 2—Model aggregation:$\mathrm{BS}\mathrm{receives}\mathrm{the}\mathrm{corresponding}{w}_{t+1}^{r}$$\mathrm{from}\mathrm{each}\mathrm{edge}\mathrm{device}r$ located in the relevant RN | |||

6 | $\mathrm{The}\mathrm{BS}\mathrm{computes}{w}_{t+1}$$\mathrm{based}\mathrm{on}\left(8\right)\mathrm{and}\mathrm{the}\mathrm{contributions}\mathrm{of}\mathrm{each}\mathrm{RN}r$ | |||

7 | $\mathrm{The}\mathrm{BS}\mathrm{estimates}\mathrm{the}\mathrm{actual}\mathrm{gradient}\mathrm{of}\mathrm{RN}(\mathrm{edge}\mathrm{device})r$ | |||

8 | Step 3—Performance Evaluation: BS computes the overall EE, SE levels | |||

9 | if$E{E}_{t+1}E{E}_{t}E{E}_{t+1}E{E}_{t}$ then | |||

10 | continue; | |||

11 | else | |||

12 | $\mathrm{reinitialize}{w}_{0}^{r}$ and go to line (3) | |||

RN Algorithm steps$(\forall r\in R$)—Edge device | ||||

1 | Step 1—Model distribution:$\mathrm{the}\mathrm{RN}\mathrm{receives}\mathrm{updated}\mathrm{global}\mathrm{model}{w}_{t}$$\mathrm{and}\mathrm{the}\mathrm{corresponding}\mathrm{learning}\mathrm{rate}{\lambda}_{t}$ from the BS | |||

2 | Step 2—Local model update:$\mathrm{the}\mathrm{RN}\mathrm{receives}\mathrm{each}\mathrm{set}\left({\mathit{i}}_{r,i},{o}_{r,i}\right)$ from the connected UEs | |||

3 | $\mathrm{The}\mathrm{RN}\mathrm{computes}{w}_{t+1}^{r}$ | |||

4 | Step 3—Local model distribution:$\mathrm{the}\mathrm{RN}\mathrm{broadcasts}{w}_{t+1}^{r}$ to the corresponding BS and UEs | |||

UE Algorithm steps$(\forall n\in N$) | ||||

1 | Step 1—Sample selection:$\mathrm{the}\mathrm{UE}\mathrm{randomly}\mathrm{selects}\mathrm{samples}\mathrm{of}\mathrm{the}\mathrm{global}\mathrm{dataset}\mathrm{to}\mathrm{form}\left({\mathit{i}}_{r,n},{o}_{r,n}\right)$ | |||

2 | Step 2—Local gradient computation | |||

3 | Step 3—Local update:$\mathrm{the}\mathrm{RN}\mathrm{receives}\mathrm{the}\mathrm{updated}{w}_{t+1}^{r}$ from the corresponding RN |

**BSs:**They broadcast the updated global model ${w}_{t}$ and the corresponding learning rate ${\lambda}_{t}$ to all edge devices located to RNs (**Step 1—Model dissemination**). Afterwards, they receive the corresponding ${w}_{t+1}^{r}$ from each edge device $r$ located in the relevant RN, compute ${w}_{t+1}$ based on (8) and the contributions of each RN $r$, and estimate the actual gradient of each RN (**Step 2—Model aggregation**). Finally, KPI evaluation is performed by the calculation of the overall EE and SE levels.**RNs:**They receive the updated global model $w\_t$ and the corresponding learning rate $\lambda \_t$ from the linked BS (**Step 1—Model distribution**). Afterward, they receive each set $\left({\mathit{i}}_{r,i},{o}_{r,i}\right)$ from the connected UEs and compute ${w}_{t+1}^{r}$ (**Step 2—Local model update**). Finally, the RN broadcasts ${w}_{t+1}^{r}$ to the linked BS and UEs (**Step 3—Local model distribution**).- UEs: They randomly select samples of the global dataset to form $\left({\mathit{i}}_{r,i},{o}_{r,i}\right)$ (
**Step 1—Sample selection**). Afterward, the compute the local gradient (**Step 2—Local gradient computation**) and, finally, receive the updated ${w}_{t+1}^{r}$ from the corresponding RN (**Step 3—Local update**).

## 4. Simulation Setup and Results

#### 4.1. Network Metrics Evaluation

**The baseline scenario with no RN deployment**: When six subcarriers are assigned per UE, EE can achieve up to 139.79/152.63 Mbps/W for FL-I/FL-O scenarios, respectively, while the No-RN scenario is limited to 23.45 Mbps/W. These figures indicate a nearly six times improvement in total EE through FL-based RN selection. For 11 subcarriers per UE, the corresponding values are 52.38/252.45/272.03 Mbps/W for No-RN/FL-I/FL-O scenarios, leading to a ~4–5 times EE enhancement. Similar enhancements are observed for SE, as shown in Figure 5, resulting in a ~4–5 times improvement.**State-of-the-art CL-based ML approaches [18]:**The EE values for scenarios in [18] are 76.95/139.79 Mbps/W for MLP-I/MLP-O scenarios, respectively. Thus, the overall EE is enhanced by ~1.5 times compared to the DRL scheme in [18]. Similarly, for 11 subcarriers per UE, the EE values for MLP-I/MLP-O scenarios are 110.34/252.45 Mbps/W, leading to a ~1–2 times EE improvement. Comparable improvements are observed for SE, as depicted in Figure 5, resulting in a ~1–2 times SE enhancement.

#### 4.2. Impact on Training Accuracy and Time

## 5. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## Acronyms

3GPP | Third Generation Partnership Project |

5G | Fifth Generation |

6G | Sixth Generation |

A&F | Amplify and Forward |

AI | Artificial Intelligence |

ANN | Artificial Neural Networks |

AP | Access Point |

AR | Augmented Reality |

B5G | Beyond Fifth Generation |

BS | Base Station |

CL | Centralized Learning |

CSI | Channel State Information |

DL | Deep Learning |

DRL | Deep Reinforcement Learning |

EE | Energy Efficiency |

eMBB | Enhanced Mobile Broadband |

FANET | Flying Ad Hoc Networks |

FL | Federated Learning |

IMT | International Mobile Telecommunications |

IoT | Internet of Things |

KPI | Key Performance Indicator |

MANET | Mobile Ad Hoc Networks |

MC | Monte Carlo |

MEC | Mobile Edge Computing |

ML | Machine Learning |

ML | Machine Learning |

m-MIMO | Multiple Input Multiple Output |

mMTC | Massive Machine-Type Communications |

mmWave | Millimeter Wave |

NG | Next Generation |

NOMA | Non-Orthogonal Multiple Access |

NTN | Non-Terrestrial Networks |

OFDMA | Orthogonal Frequency Division Multiple Access |

OSI | Open Systems Interconnection |

PLS | Physical Layer Security |

PSP | Partial Synchronization Parallel |

ReLU | Rectified Linear Unit |

RIS | Reconfigurable Intelligent Surfaces |

RL | Reinforcement Learning |

RN | Relay Node |

RRM | Radio Resource Management |

SDN | Software-Defined Network |

SE | Spectral Efficiency |

SINR | Signal-To-Interference-Plus-Noise |

SVM | Support Vector Machine |

UE | User Equipment |

URLLC | Ultra-Reliable Low-Latency Communications |

V2V | Vehicle to Vehicle |

VR | Virtual Reality |

## References

- Sudhamani, C.; Roslee, M.; Tiang, J.J.; Rehman, A.U. A Survey on 5G Coverage Improvement Techniques: Issues and Future Challenges. Sensors
**2023**, 23, 2356. [Google Scholar] [CrossRef] [PubMed] - Navarro-Ortiz, J.; Romero-Diaz, P.; Sendra, S.; Ameigeiras, P.; Ramos-Munoz, J.J.; Lopez-Soler, J.M. A Survey on 5G Usage Scenarios and Traffic Models. IEEE Commun. Surv. Tutor.
**2020**, 22, 905–929. [Google Scholar] [CrossRef] - Banda, L.; Mzyece, M.; Mekuria, F. 5G Business Models for Mobile Network Operators—A Survey. IEEE Access
**2022**, 10, 94851–94886. [Google Scholar] [CrossRef] - Interdonato, G.; Buzzi, S.; D’Andrea, C.; Venturino, L.; D’Elia, C.; Vendittelli, P. On the Coexistence of eMBB and URLLC in Multi-cell Massive MIMO. IEEE Open J. Commun. Soc.
**2023**, 4, 1040–1059. [Google Scholar] [CrossRef] - Sabuj, S.R.; Ahmed, S.; Jo, H.-S. Multiple Cuav-Enabled mMTC and URLLC Services: Review of Energy Efficiency and Latency Performance. IEEE Trans. Green Commun. Netw.
**2023**, 7, 1369–1382. [Google Scholar] [CrossRef] - Kazmi, S.H.A.; Qamar, F.; Hassan, R.; Nisar, K.; Chowdhry, B.S. Survey on Joint Paradigm of 5G and SDN Emerging Mobile Technologies: Architecture, Security, Challenges and Research Directions. Wirel. Pers. Commun.
**2023**, 130, 2753–2800. [Google Scholar] [CrossRef] - Dangi, R.; Choudhary, G.; Dragoni, N.; Lalwani, P.; Khare, U.; Kundu, S. 6G Mobile Networks: Key Technologies, Directions, and Advances. Telecom
**2023**, 4, 836–876. [Google Scholar] [CrossRef] - Ikram, M.; Sultan, K.; Lateef, M.F.; Alqadami, A.S.M. A Road towards 6G Communication—A Review of 5G Antennas, Arrays, and Wearable Devices. Electronics
**2022**, 11, 169. [Google Scholar] [CrossRef] - Bartsiokas, I.A.; Gkonis, P.K.; Papazafeiropoulos, A.K.; Kaklamani, D.I.; Venieris, I.S. Federated Learning for 6G HetNets’ Physical Layer Optimization: Perspectives, Trends, and Challenges. In Encyclopedia of Information Science and Technology, 6th ed.; Mehdi Khosrow-Pour, D.B.A., Ed.; IGI Global: Hershey, PA, USA, 2025; pp. 1–28. [Google Scholar] [CrossRef]
- Wang, C.; You, X.; Gao, X.; Zhu, X.; Li, Z.-S.; Zhang, C.; Wang, H.; Huang, Y.; Chen, Y.; Haas, H. On the Road to 6G: Visions, Requirements, Key Technologies, and Testbeds. IEEE Commun. Surv. Tutor.
**2023**, 25, 905–974. [Google Scholar] [CrossRef] - Shen, L.-H.; Feng, K.-T.; Hanzo, L. Five Facets of 6G: Research Challenges and Opportunities. ACM Comput. Surv.
**2022**, 55, 1–39. [Google Scholar] [CrossRef] - Puspitasari, A.A.; An, T.T.; Alsharif, M.H.; Lee, B.M. Emerging Technologies for 6G Communication Networks: Machine Learning Approaches. Sensors
**2023**, 23, 7709. [Google Scholar] [CrossRef] [PubMed] - Golos, E.; Daraseliya, A.; Sopin, E.; Begishev, V.; Gaidamaka, Y. Optimizing Service Areas in 6G mmWave/THz Systems with Dual Blockage and Micromobility. Mathematics
**2023**, 11, 870. [Google Scholar] [CrossRef] - Bany Salameh, H.; Abdel-Razeq, S.N.S.; Al-Obiedollah, H. Integration of Cognitive Radio Technology in Noma-Based B5G Networks: State of the Art, Challenges, and Enabling Technologies. IEEE Access
**2023**, 11, 12949–12962. [Google Scholar] [CrossRef] - Lavdas, S.; Gkonis, P.K.; Tsaknaki, E.; Sarakis, L.; Trakadas, P.; Papadopoulos, K. A Deep Learning Framework for Adaptive Beamforming in Massive MIMO Millimeter Wave 5G Multicellular Networks. Electronics
**2023**, 12, 3555. [Google Scholar] [CrossRef] - Mitev, M.; Chorti, A.; Poor, H.V.; Fettweis, G. What Physical Layer Security Can Do for 6G Security. IEEE Open J. Veh. Technol.
**2023**, 4, 375–388. [Google Scholar] [CrossRef] - Papazafeiropoulos, A.K.; Tran, L.-N.; Abdullah, Z.Q.; Kourtessis, P.; Chatzinotas, S. Achievable Rate of a STAR-RIS Assisted Massive MIMO System Under Spatially-correlated Channels. IEEE Trans. Wirel. Commun.
**2023**. [Google Scholar] [CrossRef] - Bartsiokas, I.A.; Gkonis, P.K.; Kaklamani, D.I.; Venieris, I.S. A DL-enabled Relay Node Placement and Selection Framework in Multicellular Networks. IEEE Access
**2023**, 11, 65153–65169. [Google Scholar] [CrossRef] - Bartsiokas, I.A.; Gkonis, P.K.; Kaklamani, D.I.; Venieris, I.S. Ml-based Radio Resource Management in 5G and Beyond Networks: A Survey. IEEE Access
**2023**, 10, 83507–83528. [Google Scholar] [CrossRef] - Mahmood, M.R.; Matin, M.; Sarigiannidis, P.; Goudos, S.K. A Comprehensive Review on Artificial Intelligence/Machine Learning Algorithms for Empowering the Future IoT toward 6G Era. IEEE Access
**2022**, 10, 87535–87562. [Google Scholar] [CrossRef] - Cardoso, C.M.M.; Barros, F.J.B.; Carvalho, J.A.R.; Machado, A.A.; Cruz, H.A.O.; de Alcântara Neto, M.C.; Araújo, J.P.L. SNR Prediction with ANN for UAV Applications in IoT Networks Based on Measurements. Sensors
**2022**, 22, 5233. [Google Scholar] [CrossRef] - Gonzalez-Franco, J.D.; Preciado-Velasco, J.E.; Lozano-Rizk, J.E.; Rivera-Rodriguez, R.; Torres-Rodriguez, J.; Alonso-Arevalo, M.A. Comparison of Supervised Learning Algorithms on a 5G Dataset Reduced via Principal Component Analysis (PCA). Future Internet
**2023**, 15, 335. [Google Scholar] [CrossRef] - Yang, F.; Yang, C.; Huang, J.; Yu, K.; Garg, S.; Alrashoud, M. Hypergraph Based Resource-Efficient Collaborative Reinforcement Learning for B5G Massive IoT. IEEE Open J. Commun. Soc.
**2023**, 4, 2439–2450. [Google Scholar] [CrossRef] - Huang, C.-W.; Althamary, I.; Chou, Y.-C.; Chen, H.-Y.; Chou, C.-F. A DRL-based Automated Algorithm Selection Framework for Cross-Layer Qos-Aware Scheduling and Antenna Allocation in Massive MIMO Systems. IEEE Access
**2023**, 11, 13243–13256. [Google Scholar] [CrossRef] - Elbir, A.M.; Papazafeiropoulos, A.K.; Chatzinotas, S. Federated learning for physical layer design. IEEE Commun. Mag.
**2021**, 11, 81–87. [Google Scholar] [CrossRef] - Salh, A.; Ngah, R.; Audah, L.; Kim, K.S.; Abdullah, Q.; Al-Moliki, Y.M.; Aljaloud, K.; Talib, H.N. Energy-efficient Federated Learning with Resource Allocation for Green Iot Edge Intelligence in B5G. IEEE Access
**2023**, 11, 16353–16367. [Google Scholar] [CrossRef] - Al-Quraan, M.; Mohjazi, L.; Bariah, L.; Centeno, A.; Zoha, A.; Arshad, K.; Assaleh, K.; Muhaidat, S.; Debbah, M.; Imran, M.A. Edge-native intelligence for 6G communications driven by federated learning: A survey of trends and challenges. IEEE Trans. Emerg. Top. Comput. Intell.
**2023**, 7, 957–979. [Google Scholar] [CrossRef] - McMahan, B.; Moore, E.; Ramage, D.; Hampson, S.; Arcas, B.A. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the Artificial Intelligence and Statistics (AISTAS), Ft. Lauderdale, FL, USA, 20–22 April 2017; pp. 1273–1282. [Google Scholar]
- Chen, H.; Xiao, M.; Pang, Z. Satellite-based computing networks with federated learning. IEEE Wirel. Commun.
**2021**, 29, 78–84. [Google Scholar] [CrossRef] - Yang, Z.; Chen, M.; Liu, X.; Liu, Y.; Chen, Y.; Cui, S.; Poor, H.V. AI-driven UAV-NOMA-MEC in Next Generation Wireless Networks. IEEE Wirel. Commun.
**2021**, 28, 66–73. [Google Scholar] [CrossRef] - Nyangaresi, V.O.; Rodrigues, A.J.; Abeka, S.O. ANN-FL secure handover protocol for 5G and beyond networks. In Proceedings of the Towards New e-Infrastructure and e-Services for Developing Countries: 12th EAI International Conference, AFRICOMM 2020, Ebène City, Mauritius, 2–4 December 2020; Springer International Publishing: Berlin/Heidelberg, Germany, 2020; pp. 99–118. [Google Scholar]
- Wasilewska, M.; Bogucka, H.; Kliks, A. Federated Learning for 5G Radio Spectrum Sensing. Sensors
**2022**, 22, 198. [Google Scholar] [CrossRef] - Yu, S.; Chen, X.; Zhou, Z.; Gong, X.; Wu, D. When deep reinforcement learning meets federated learning: Intelligent multitimescale resource management for multiaccess edge computing in 5G ultradense network. IEEE Internet Things J.
**2020**, 8, 2238–2251. [Google Scholar] [CrossRef] - Yang, H.H.; Liu, Z.; Quek, T.Q.S.; Poor, H.V. Scheduling Policies for Federated Learning in Wireless Networks. IEEE Trans Commun.
**2020**, 68, 317–333. [Google Scholar] [CrossRef] - Bhattacharya, A.; Kumar, A. A shortest path tree based algorithm for relay placement in a wireless sensor network and its performance analysis. Comput. Netw.
**2014**, 71, 48–62. [Google Scholar] [CrossRef] - Xu, W.; Yang, Z.; Ng, D.W.K.; Levorato, M.; Eldar, Y.C.; Debbah, M. Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing. IEEE J. Sel. Top. Signal Process.
**2022**, 17, 9–39. [Google Scholar] [CrossRef] - Feng, S.; Niyato, D.; Wang, P.; Kim, D.; Liang, Y. Joint Service Pricing and Cooperative Relay Communication for Federated Learning. In Proceedings of the 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA, 14–17 July 2019; pp. 815–820. [Google Scholar] [CrossRef]
- Khowaja, S.A.; Dev, K.; Khowaja, P.; Bellavista, P. Toward energy-efficient distributed federated learning for 6G networks. IEEE Wirel. Commun.
**2021**, 28, 34–40. [Google Scholar] [CrossRef] - Al-Abiad, M.S.; Hassan, M.Z.; Hossain, M.J. Energy-Efficient Resource Allocation for Federated Learning in NOMA-Enabled and Relay-Assisted Internet of Things Networks. IEEE Internet Things J.
**2022**, 9, 24736–24753. [Google Scholar] [CrossRef] - Zhang, X.; Chen, R.; Wang, J.; Zhang, H.; Pan, M. Energy Efficient Federated Learning over Cooperative Relay-Assisted Wireless Network. In Proceedings of the 2022 IEEE Global Communications Conference, Rio de Janeiro, Brazil, 4–8 December 2022; pp. 179–184. [Google Scholar] [CrossRef]
- Lin, Z.; Liu, H.; Zhang, Y.J.A. Relay-assisted cooperative federated learning. IEEE Trans. Wirel. Commun.
**2022**, 21, 7148–7164. [Google Scholar] [CrossRef] - Qu, Z.; Guo, S.; Wang, H.; Ye, B.; Wang, Y.; Zomaya, A.Y.; Tang, B. Partial synchronization to accelerate federated learning over relay-assisted edge networks. IEEE Trans. Mob. Comput.
**2021**, 21, 4502–4516. [Google Scholar] [CrossRef] - Iqbal, A.; Tham, M.L.; Chang, Y.C. Resource allocation for joint energy and spectral efficiency in cloud radio access network based on deep reinforcement learning. Trans. Emerg. Telecommun. Technol.
**2021**, 33, e12490. [Google Scholar] [CrossRef] - Iqbal, A.; Tham, M.-L.; Chang, Y.C. Energy- and Spectral- Efficient Optimization in Cloud RAN based on Dueling Double Deep Q-Network. In Proceedings of the 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS), Shah Alam, Malaysia, 26 June 2021; pp. 311–316. [Google Scholar] [CrossRef]
- Chen, Z.; Hu, J.; Min, G.; Luo, C.; El-Ghazawi, T. Adaptive and Efficient Resource Allocation in Cloud Datacenters Using Actor-Critic Deep Reinforcement Learning. IEEE Trans. Parallel Distrib. Syst.
**2022**, 33, 1911–1923. [Google Scholar] [CrossRef] - Chen, Z.; Hu, J.; Min, G. Learning-Based Resource Allocation in Cloud Data Center using Advantage Actor-Critic. In Proceedings of the IEEE International Conference on Communications (ICC), Shanghai, China, 20–24 May 2019; pp. 1–6. [Google Scholar] [CrossRef]
- Chen, X.; Yang, L.; Chen, Z.; Min, G.; Zheng, X.; Rong, C. Resource Allocation with Workload-Time Windows for Cloud-Based Software Services: A Deep Reinforcement Learning Approach. IEEE Trans. Cloud Comput.
**2023**, 11, 1871–1885. [Google Scholar] [CrossRef] - Psilopanagiotis, K.A.; Bartsiokas, I.A.; Gkonis, P.K.; Kaklamani, D.I. On relay-based subcarrier allocation and power management in 5G multicellular networks. In Proceedings of the 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring), Helsinki, Finland, 19–22 June 2022; pp. 1–6. [Google Scholar] [CrossRef]
- Li, Y.; Pateromichelakis, E.; Vucic, N.; Luo, J.; Xu, W.; Caire, G. Radio resource management considerations for 5G millimeter wave backhaul and access networks. IEEE Commun. Mag.
**2017**, 55, 86–97. [Google Scholar] [CrossRef] - Samidi, F.S.; Mohamed Radzi, N.A.; Mohd Azmi, K.H.; Mohd Aripin, N.; Azhar, N.A. 5G technology: ML hyperparameter tuning analysis for subcarrier spacing prediction model. Appl. Sci.
**2022**, 12, 8271. [Google Scholar] [CrossRef] - Study on Channel Model for Frequencies from 0.5 to 100 GHz, Document 3GPP TR 38.901, Release 17, 2023. Available online: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=3173 (accessed on 19 December 2023).
- 5G NR Physical Channels and Modulation, document 3GPP TS 138 211, Version 15.3.0, Release 17, 2023. Available online: https://www.etsi.org/deliver/etsi_ts/138200_138299/138211/15.03.00_60/ts_138211v150300p.pdf (accessed on 19 December 2023).
- BenMimoune, A.; Kadoch, M. Relay technology for 5G networks and IoT applications. In Internet of Things: Novel Advances and Envisioned Applications; Springer: Cham, Switzerland, 2017; pp. 3–26. [Google Scholar]
- Release Notes for MATLAB—MATLAB & Simulink. Available online: https://www.mathworks.com/help/matlab/release-notes.html (accessed on 19 December 2023).

**Figure 1.**CL versus FL in B5G/6G multicellular networks. (

**a**) CL-based architecture; (

**b**) FL-based architecture.

**Figure 6.**Test accuracy for mean total SE for the RN implementation scenarios under test (CL-based training [18], FL-based training).

Aspect | CL | FL |
---|---|---|

Data Privacy | May raise privacy concerns as centralized processing involves accessing raw data from multiple sources. | Raw data remain on local devices, and only model updates are exchanged, preserving data privacy. |

Communication Overhead | Lower communication overhead as all data are in one location. | Higher communication overhead due to the need to send model updates across decentralized devices, impacting latency. |

Scalability | May face scalability issues as the central entities handle all data. | Generally more scalable as decentralized learning can be distributed across a large number of devices in B5G/6G networks. |

Data Efficiency | Efficient use of data since all data are available in one place. | May require more data due to decentralized training, potentially posing challenges in scenarios with limited data on individual devices. |

Model Robustness | Centralized model may lack robustness if not trained on diverse data. | Encourages model robustness by training on diverse local data, potentially enhancing adaptability to heterogeneous network conditions. |

Security | Vulnerable to security breaches as all data are in one location. | More secure in terms of data privacy since raw data stay on local devices, reducing the risk of a centralized data breach in 5G/6G networks. |

Features | Description |
---|---|

$U{E}_{x}$ | x-axis position of the UE |

$U{E}_{y}$ | y-axis position of the UE |

$U{E}_{z}$ | z-axis position of the UE |

$B{S}_{serve}$ | ID of the server BS |

$B{S}_{sec}$ | Serving sector of the UE |

$P{L}_{mat}$ | $Rx1$ path loss matrix between the UE and all available RNs |

$T{L}_{mat}$ | $Rx1$ total losses matrix between the UE and all available RNs |

${\mathit{H}}_{matrix}$ | ${M}_{r}x{M}_{t}$ channel coefficient matrix |

${RN}_{serve}$ | ID of the RN that serves the UE |

Features | Description |
---|---|

Tier/number of cells | 2/19 |

Carrier frequency | 28 GHz |

Number of antennas per BS/RN/UE | 4/2/1 |

Cell radius | $500\sqrt{3}$ m |

BS/RN/UE antenna height | 25/5/1.5 m |

UE indoor-to-outdoor ratio | 0.8/0.2 |

LOS Probability for BS-UE/BS-RN/RN-UE links | 15%/11%/10% [52] |

Maximum allowed path loss BS/RN | 120/320 dB |

Antenna gains BS/RN/UE | 18/9/4 |

Requested subcarriers per UE | 6/8/11 |

Number of subcarriers per BS | 132 |

Subcarrier spacing | 60 kHz |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Bartsiokas, I.A.; Gkonis, P.K.; Kaklamani, D.I.; Venieris, I.S.
A Federated Learning-Based Resource Allocation Scheme for Relaying-Assisted Communications in Multicellular Next Generation Network Topologies. *Electronics* **2024**, *13*, 390.
https://doi.org/10.3390/electronics13020390

**AMA Style**

Bartsiokas IA, Gkonis PK, Kaklamani DI, Venieris IS.
A Federated Learning-Based Resource Allocation Scheme for Relaying-Assisted Communications in Multicellular Next Generation Network Topologies. *Electronics*. 2024; 13(2):390.
https://doi.org/10.3390/electronics13020390

**Chicago/Turabian Style**

Bartsiokas, Ioannis A., Panagiotis K. Gkonis, Dimitra I. Kaklamani, and Iakovos S. Venieris.
2024. "A Federated Learning-Based Resource Allocation Scheme for Relaying-Assisted Communications in Multicellular Next Generation Network Topologies" *Electronics* 13, no. 2: 390.
https://doi.org/10.3390/electronics13020390