ECO6G: Energy and Cost Analysis for Network Slicing Deployment in Beyond 5G Networks
Abstract
:1. Introduction
2. Contribution
- We have evaluated our proposed ECO6G model against the traditional deep learning neural network (DLNN) with random weights and statistical time-series modeling, i.e., Auto-Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) in Section 6.
3. Related Work
4. Motivation for Energy Efficiency Using Data-Driven Learning
5. Current Energy and Power Challenges in Beyond 5G Networks
6. Proposed ECO6G Framework
7. Process Flow for ECO6G Framework
- Step I
- The ECO6G framework initializes by training the traditional neural model using observed RRC, number of PDU sessions, and the total network load from all Slices—A (eMBB), B (mIoT), and C (URLLC), i.e., . Network operators can deploy many slices; we are considering three standard slices for our evaluation per standardized 3GPP SST values. We have employed five-layer DNN: Input (features), three Hidden Layers, and Output (prediction). We have tuned the model hyper-parameters by changing the number of hidden layers, learning rate, activation function, and the number of epochs for the model in MATLAB using Deep Learning Toolbox and Alteryx Analytics Automation tool running on Intel hardware and Windows 11 operating system. Our goal is to validate the model performance between random weights and learned weights, so we kept the DNN modeling the same for both and . The algorithm uses randomness to find a good set of weights for the specific input–output mapping function of the data, such that each time the training algorithm is run, a different network with a different model is fitted. The shuffling of the training dataset before each epoch also uses randomness, resulting in differences in the gradient estimate for each batch.
- Step II
- First, we train the multi-layer model using a feed-forward backpropagation network with initialized random weights (stochastic gradient descent). A forward pass through the network is accomplished by iteratively computing each neuron in the subsequent layer until the output is achieved. We evaluate the output quality based on a cost function C and the desired result in the output layer. Mean squared error (MSE) is used as a loss function for evaluation.
- Step III
- A backward pass is then used to optimize the cost function C after the first result has been obtained by readjusting the weights and biases. We aim to optimize the output by adjusting the entire neural network. Based on this, we can calculate the total loss and determine the model’s suitability (good or bad), and here, weights are adjusted to achieve a minimum loss. After backpropagation, we capture each layer’s computed weights (learned weights) for TL parameters and define these trained weights as .
- Step IV
- Now, training the with ‘random weights’, we initialize using learned weights and re-train for smaller datasets , , from individual slices, which are subsets of to predict total network load.
Algorithm 1 ECO6G Training and Validation |
1: Set parameters 2: (0, 1): weights/parameters 3: b ∈ (0, 1): bias 4: (0, 1): learning rate to control change in and b 5: (0, 1): sigmoid activation function 6: where is the input, consisting of RRC, RSSNSI and PDU of each of the three slices from the network and devices 7: Weighted sum value 8: Training data for the network load of size 7729 X 9 9: Training data for the network load of size 169 X 9 10: Initialization of the multi-layer model, consisting of parameters in [0, 1] 11: Training of with 12: Predicting the network load with error function 13: Optimization of cost function through back propagation and gradient descent with in step 12 until convergence 14: Selection of the learned parameters representing the pre-trained model as 15: Using the parameters for validating where |
8. ECO6G Framework Evaluation
9. Experimentation Results of Cost–Benefit Analysis
10. Plausible ECO6G Use Cases in B5G Implementation
11. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Delaporte, A.; Bahia, K. The State of Mobile Internet Connectivity Report 2021. GSMA, 1 September 2021. Available online: https://www.gsma.com (accessed on 27 October 2022).
- Scharp, M.P.; Persson, O. Why We Need a New Approach to Network Energy Efficiency. Available online: https://www.ericsson.com/en/blog/2020/3/5g-network-energy-efficiency (accessed on 27 October 2022).
- Kolta, E.; Hatt, T. Using AI to Improve Energy Efficiency. Available online: https://pages.nokia.com/T006SN-Using-AI-to-Improve-Energy-Efficiency.html (accessed on 27 October 2022).
- Peesapati, S.K.G.; Olsson, M.; Masoudi, M.; Andersson, S.; Cavdar, C. An Analytical Energy Performance Evaluation Methodology for 5G Base Stations. In Proceedings of the 2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Bologna, Italy, 11–13 October 2021; pp. 169–174. [Google Scholar] [CrossRef]
- Lorincz, J.; Klarin, Z.; Begusic, D. Modeling and Analysis of Data and Coverage Energy Efficiency for Different Demographic Areas in 5G Networks. IEEE Syst. J. 2022, 16, 1056–1067. [Google Scholar] [CrossRef]
- ETSI. Environmental Engineering (EE); Metrics and Measurement Method for Energy Efficiency of Wireless Access Network Equipment. 1 January 2021. Available online: https://www.etsi.org/deliver/etsi_es/202700_202799/20270601/01.06.01_60/es_20270601v010601p.pdf (accessed on 27 October 2022).
- ETSI. Environmental Engineering (EE); Sustainable Power Feeding Solutions for 5G Network. 1 February 2021. Available online: https://www.etsi.org/deliver/etsi_es/203700_203799/203700/01.01.01_60/es_203700v010101p.pdf (accessed on 27 October 2022).
- Release 17. 21 October 2022. Available online: https://www.3gpp.org/specifications-technologies/releases/release-17 (accessed on 27 October 2022).
- Thantharate, A.; Paropkari, R.; Walunj, V.; Beard, C. DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks. In Proceedings of the 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, NY, USA, 10–12 October 2019; pp. 0762–0767. [Google Scholar] [CrossRef]
- Thantharate, A.; Paropkari, R.; Walunj, V.; Beard, C.; Kankariya, P. Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond. In Proceedings of the 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 6–8 January 2020; pp. 852–857. [Google Scholar] [CrossRef]
- Cui, Y.; Huang, X.; Wu, D.; Zheng, H. Machine Learning-Based Resource Allocation Strategy for Network Slicing in Vehicular Networks. Hindawi Wirel. Commun. Mob. Comput. 2020, 2020, 8836315. [Google Scholar] [CrossRef]
- Abidi, M.H.; Alkhalefah, H.; Moiduddin, K.; Alazab, M.; Mohammed, M.K.; Ameen, W.; Gadekallu, T.R. Optimal 5G network slicing using machine learning and deep learning concepts. Comput. Stand. Interface 2021, 76, 103518. [Google Scholar] [CrossRef]
- Mai, T.; Yao, H.; Zhang, N.; He, W. Transfer Reinforcement Learning aided Distributed Network Slicing Optimization in Industrial IoT. IEEE Trans. Ind. Inform. 2021, 18, 4308–4316. [Google Scholar] [CrossRef]
- Nagib, A.M.; Abou-zeid, H.; Hassanein, H.S. Transfer Learning-Based Accelerated Deep Reinforcement Learning for 5G RAN Slicing. In Proceedings of the 2021 IEEE 46th Conference on Local Computer Networks (LCN), Edmonton, AB, Canada, 4–7 October 2021. [Google Scholar] [CrossRef]
- Mason, F.; Nencioni, G.; Zanella, A. Using Distributed Reinforcement Learning for Resource Orchestration in a Network Slicing Scenario. arXiv 2021, arXiv:2105.07946v1. [Google Scholar] [CrossRef]
- Mei, J.; Wang, X.; Zheng, K. An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks. Intell. Converg. Netw. 2020, 1, 281–294. [Google Scholar] [CrossRef]
- Chergui, H.; Verikoukis, C. Big Data for 5G Intelligent Network Slicing Management. IEEE Netw. 2020, 34, 56–61. [Google Scholar] [CrossRef]
- Zhou, H.; Erol-Kantarci, M.; Poor, V. Learning from Peers: Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G Network Slicing. arXiv 2021, arXiv:2109.07999v1. [Google Scholar] [CrossRef]
- Salahdine, F.; Opadere, J.; Liu, Q.; Han, T.; Zhang, N.; Wu, S. A survey on sleep mode techniques for ultra-dense networks in 5G and beyond. Comput. Netw. 2021, 201, 108567. [Google Scholar] [CrossRef]
- Azimi, Y.; Yousefi, S.; Kalbkhani, H.; Kunz, T. Energy-Efficient Deep Reinforcement Learning Assisted Resource Allocation for 5G-RAN Slicing. IEEE Trans. Veh. Technol. 2021, 71, 856–871. [Google Scholar] [CrossRef]
- Guo, Q.; Gu, R.; Wang, Z.; Zhao, T.; Ji, Y.; Kong, J.; Gour, R.; Jue, J.P. Proactive Dynamic Network Slicing with Deep Learning Based Short-Term Traffic Prediction for 5G Transport Network. In Proceedings of the 2019 International Conference on Optical Communications and Networks, San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Wang, W.; Chen, Q.; Member, S.; Tang, L. Cooperative Anomaly Detection With Transfer Learning-Based Hidden Markov Model in Virtualized Network Slicing. IEEE Commun. Lett. 2019, 23, 1534–1537. [Google Scholar] [CrossRef]
- Lei, L.; Yuan, Y.; Vu, T.X.; Chatzinotas, S.; Minardi, M.; Montoya, J.F.M. Dynamic-Adaptive AI Solutions for Network Slicing Management in Satellite-Integrated B5G Systems. IEEE Netw. 2021, 35, 91–97. [Google Scholar] [CrossRef]
- Martin-Perez, J.; Malandrino, F.; Chiasserini, C.F.; Bernardos, C.J. OKpi: All-KPI Network Slicing Through Efficient Resource Allocation. arXiv 2020, arXiv:1912.03159. [Google Scholar]
- Gao, Y.; Zhang, M.; Chen, J.; Han, J.; Qiu, D.L.R. Accurate Load Prediction Algorithms Assisted with Machine Learning for Network Traffic. In Proceedings of the 2021 International Wireless Communications and Mobile Computing (IWCMC), Harbin, China, 28 June–2 July 2021. [Google Scholar]
- Tipantuña, C.; Hesselbach, X. Adaptive Energy Management in 5G Network Slicing: Requirements, Architecture, and Strategies. Energies 2020, 13, 3984. [Google Scholar] [CrossRef]
- Oladejo, S.; Falowo, O. An Energy-Efficient Resource Allocation Scheme for 5G Slice Networks. In Proceedings of the Southern Africa Telecommunication Networks and Applications Conference (SATNAC), Ballito, South Africa, 1–4 September 2019. [Google Scholar]
- Medeiros, G.O.; Costa, J.C.W.A.; Cardoso, D.L.; Santos, A.D.F. An Intelligent SDN Framework Based on QoE Predictions for Load Balancing in C-RAN. Hindawi Wirel. Commun. Mob. Comput. 2020, 2020, 7065202. [Google Scholar] [CrossRef]
- Sheena, B.G.; Snehalatha, N. An Energy Efficient Network Slicing with Data Aggregation Technique for Wireless Sensor Networks. In Proceedings of the Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV 2021), Tirunelveli, India, 4–6 February 2021. [Google Scholar]
- Amarasinghe, K.; Marino, D.L.; Manic, M. Deep Neural Networks for Energy Load Forecasting. In Proceedings of the 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE), Edinburgh, UK, 19–21 June 2017. [Google Scholar]
- Wang, Q.; Fu, J.; Wu, J.; Moran, B.; Zukerman, M. Energy-Efficient Priority-Based Scheduling for Wireless Network Slicing. In Proceedings of the 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, United Arab Emirates, 9–13 December 2018. [Google Scholar]
- Chergui, H.; Verikoukis, C. OPEX-Limited 5G RAN Slicing: An Over-Dataset Constrained Deep Learning Approach. In Proceedings of the IEEE International Conference on Communications (ICC), Dublin, Ireland, 7–11 June 2020. [Google Scholar]
- Sesto-Castilla, D.; Garcia-Villegas, E.; Lyberopoulos, G.; Theodoropoulou, E. Use of Machine Learning for energy efficiency in present and future mobile networks. In Proceedings of the 2019 IEEE Wireless Communications and Networking Conference (WCNC), Marrakesh, Morocco, 15–18 April 2019. [Google Scholar]
- Khan, S.; Khan, S.; Ali, Y.; Khalid, M.; Ullah, Z.; Mumtaz, S. Highly Accurate and Reliable Wireless Network Slicing in 5th Generation Networks: A Hybrid Deep Learning Approach. J. Netw. Syst. Manag. 2022, 30, 29. [Google Scholar] [CrossRef]
- Zhou, J.; Zhao, W.; Chen, S. Dynamic Network Slice Scaling Assisted byPrediction in 5G Network. IEEE Access 2020, 8, 133700–133712. [Google Scholar] [CrossRef]
- Salhab, N.; Langar, R.; Rahim, R.; Cherrier, S.; Outtagarts, A. Autonomous Network Slicing Prototype Using Machine-Learning-Based Forecasting for Radio Resources. IEEE Commun. Mag. 2021, 59, 73–79. [Google Scholar] [CrossRef]
- Singh, S.K.; Salim, M.M.; Cha, J.; Pan, Y.; Park, J.H. Machine Learning-Based Network Sub-Slicing Framework in a Sustainable 5G Environment. Sustainability 2020, 12, 6250. [Google Scholar] [CrossRef]
- Li, X.; Samaka, M.; Chan, H.A.; Bhamare, D.; Gupta, L.; Gua, C.; Jain, R. Network SLicing for 5G: CHallenges and opportunities. IEEE Comput. Soc. 2017, 21, 20–27. [Google Scholar] [CrossRef]
- Kourtis, M.A.; Sarlas, T.; Xilouris, G.; Batistatos, M.C.; Zarakovitis, C.C.; Chochliouros, I.P.; Koumaras, H. Conceptual Evaluation of a 5G Network Slicing Technique for Emergency Communications and Preliminary Estimate of Energy Trade-Off. Energies 2021, 14, 6876. [Google Scholar] [CrossRef]
- Rathore, S.; Park, J.H.; Chnag, H. Deep Learning and Blockchain-Empowered Security Framework for Intelligent 5G-Enabled IoT. IEEE Access 2021, 9, 90075–90083. [Google Scholar] [CrossRef]
- Sharma, P.K.; Ark, J.P.; Park, J.H.; Cho, K. Wearable Computing for Defence Automation:Opportunities and Challenges in 5G Network. IEEE Access 2020, 8, 65993–66002. [Google Scholar] [CrossRef]
- Park, J.H.; Rathore, S.; Singh, S.K.; Salim, M.M.; Azzaoui, A.E.L.; Kim, T.W.; Pan, Y.; Park, J.H. A Comprehensive Survey on Core Technologies and Services for 5G Security: Taxonomies, Issues, and Solutions. Hum.-Centric Comput. Inf. Sci. 2021, 11. [Google Scholar] [CrossRef]
- Piovesan, N.; De Domenico, A.; Bernabé, M.; López-Pérez, D.; Baohongqiang, H.; Xinli, G.; Xie, W.; Debbah, M. Forecasting Mobile Traffic to Achieve Greener 5G Networks: When Machine Learning is Key. In Proceedings of the 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Lucca, Italy, 27–30 September 2021; pp. 276–280. [Google Scholar] [CrossRef]
- Liu, Z.; Gao, Y.; Li, D.; Chen, J.; Han, J. Enabling energy efficiency in 5G network. ZTE Commun. 2021, 19, 20–29. [Google Scholar] [CrossRef]
- Prasad, K.N.R.S.V.; Hossain, E.; Bhargava, V.K. Energy Efficiency in Massive MIMO-Based 5G Networks: Opportunities and Challenges. TEEE Wirel. Commun. 2017, 24, 86–94. [Google Scholar] [CrossRef] [Green Version]
- von Perner, J.; Friderikos, V. Green Future Networksc- Network Energy Efficiency. Available online: https://www.ngmn.org/wp-content/uploads/211009-GFN-Network-Energy-Efficiency-1.0.pdf (accessed on 27 October 2022).
- Huawei, 5G Power Whitepaper. Available online: https://carrier.huawei.com/~/media/CNBG///Downloads/Spotlight/5g/5G-Power-White-Paper-en.pdf (accessed on 27 October 2022).
- Greenpeace East Asia. Electricity Consumption from China’s Digital Sector. Greenpeace East Asia. 28 May 2021. Available online: https://www.greenpeace.org/eastasia/press/6608///electricity-consumption-from-chinas-digital-sector-on-track-to-increase/ (accessed on 27 October 2022).
- ECO6G Dataset—Energy Efficient Beyond 5G Networks. Available online: www.kaggle.com/datasets/anuragthantharate/eco6G (accessed on 27 October 2022).
- ETSI. 5G; Management and Orchestration; 5G End to End Key Performance Indicators (KPI). 1 January 2021. Available online: https://www.etsi.org/deliver/etsi_ts/128500_128599/128554/16.07.00_60/ts_128554v160700p.pdf (accessed on 27 October 2022).
- Thantharate, A.; Beard, C. ADAPTIVE6G: Adaptive Resource Management for Network Slicing Architectures in Current 5G and Future 6G Systems. J. Netw. Syst. Manag. 2023, 31, 9. [Google Scholar] [CrossRef]
- Nguyen, C.T.; Van Huynh, N.; Chu, N.H.; Saputra, Y.M.; Hoang, D.T.; Nguyen, D.N.; Pham, Q.V.; Niyato, D.; Dutkiewicz, E.; Hwang, W.J. Transfer learning for future wireless networks: A comprehensive survey. arXiv 2021, arXiv:2102.07572. [Google Scholar]
- EIA. Electric Power Monthly—U.S. Energy Information Administration. 9 June 2022. Available online: https://www.eia.gov/electricity/monthly/epm_table_grapher.php?t=epmt_5_6_a (accessed on 15 June 2022).
Sr. No. | Related Work | ECO6G Work |
---|---|---|
[11] | Use of the cellular traffic types (SMS, phone and web), to train LSTM for slice resource allocation | Use of the network KPIs:RRC, RSSNI and PDU to train a DNN for predicting total load estimation |
[12] | 5G network slicing model using the DBN and NN to improve accuracy | TL-based DNN model for improving 5G energy efficiency and ensuring faster convergence |
[13] | DDPG slice optimization and TL based multi agent DDPG (TMDDPG) for accelerated learning by evaluating delay, EE, and PLR for DDPG, DQN and TMDDPG | Evaluation of ARIMA, ETS, and DL models to investigate traffic forecasting for enhanced 5G EE |
[14] | DRL based 5G RAN slicing resource allocation and TL to accelerate the learning and tackle slow convergence | Use of TL with DNN to estimate the network load using slicing KPIs, to estimate the EE and improved convergence rate |
[15] | TL-based A2C approach to increase network utility at the expense of reduced adaptability of the various network topologies. | TL approach to improve energy efficiency with an approximate OPEX savings of seven hundred eighty-six million for the MNOs in off-peak network load scenarios |
[16] | RAN slicing architecture for autonomous learning in interference affected and the TL approach to facilitate self-learning RAN slicing control. | The work in [16] targets autonomous RAN slicing, whereas our work uses the data driven model trained on the network KPIs to estimate the EE of 5G networks |
[17] | Dynamic slicing resource allocation with an hourly dataset of a live cellular network attributes recorded over five days for sites in dense urban areas fed directly to the GRU | Our dataset is captured on a real-world 5G BS using the MNO’s proprietary software, including data for three sectors and network KPIs from each sector |
[18] | Comparative analysis of the transfer RL (TRL), Q-value TRL and action selection TRL with model-free Q-learning and the model-based priority proportional fairness and time-to-live (PPF-TTL) to solve for slow convergence and lack of generalization of RL techniques | In contrast to [18], our work addresses the issue of slow convergence by proposing a comparative analysis of our ECO6G model with ARIMA, ETS, and DNN with random weights |
[19] | Use of techniques for enabling sleep mode methods in heterogeneous mobile networks with the aim of reducing power consumption | Our work proposes to enhance the energy efficiency of the 5G network with an OPEX saving from the perspective of MNOs |
[20] | EE DRL based resource allocation for RAN slicing to improve computational and time complexity | Data driven approach for improved OPEX savings against the conventional approaches for MNOS in varying load |
[21] | DL based network slicing short-term traffic prediction for 5G transport network | Supervised ML model for forecasting traffic load and using the estimated load to evaluate EE and improve OPEX savings by a margin of 48.67% against other evaluated data-driven models |
Average Load % | Low Load (6/24) | Medium Load (10/24) | High Load (8/24) |
Actual | 42.53 | 74.36 | 88.23 |
43.1 | 75.65 | 89.04 | |
ECO6G | 43.03 | 75.21 | 88.96 |
ARIMA | 42.01 | 73.92 | 87.63 |
ETS | 43.6 | 75.4 | 88.84 |
Peak Load % | Low Load (6/24) | Medium LOAD (10/24) | High LOAD (8/24) |
Actual | 73.86 | 94.50 | 99.60 |
74.44 | 95.32 | 99.59 | |
ECO6G | 74.48 | 95.23 | 99.78 |
ARIMA | 75.39 | 92.96 | 96.86 |
ETS | 75.15 | 94.21 | 99.61 |
Peak Bits/Watts | Low Load (6/24) | Medium Load (10/24) | High Load (8/24) | Total |
---|---|---|---|---|
Actual | 6690.22 | 6788.79 | 5928.57 | 6477.41 |
6742.75 | 6847.70 | 5927.98 | 6514.89 | |
ECO6G | 6746.38 | 6841.24 | 5939.29 | 6516.87 |
ARIMA | 6828.80 | 6678.16 | 5765.48 | 6411.59 |
ETS | 6807.07 | 6767.96 | 5929.17 | 6498.14 |
Power Consumption (in kW) | Low Load (6/24) | Medium Load (10/24) | High Load (8/24) | Total |
---|---|---|---|---|
Actual | 6.36 | 10.95 | 14.88 | 11.11 |
6.39 | 11.05 | 15.02 | 11.21 | |
ECO6G | 6.38 | 10.99 | 14.98 | 11.17 |
ARIMA | 6.15 | 11.07 | 15.20 | 11.22 |
ETS | 6.41 | 11.14 | 14.98 | 11.24 |
OPEX Cost per BS ($) | Low Load (6/24) | Medium Load (10/24) | High Load (8/24) | Weighted Avg for 24 h |
---|---|---|---|---|
Actual | 34,297.91 | 56,244.90 | 77,801.83 | 57,943.80 |
34,561.10 | 56,764.43 | 78,064.91 | 58,313.76 | |
ECO6G | 34,234.89 | 56,167.78 | 77,932.57 | 57,939.49 |
ARIMA | 36,089.28 | 57,722.90 | 78,865.72 | 59,632.10 |
ETS | 36,729.73 | 58,272.96 | 79,048.24 | 59,812.24 |
OPEX Cost Change across Models | Low Load (6/24) | Medium Load (10/24) | High Load (8/24) | Weighted Avg for 24 h (Also Compared with ECO6G) |
---|---|---|---|---|
263.19 | 519.53 | 263.09 | 369.96 (+374.27) | |
ECO6G | −63.02 | −77.12 | 130.74 | −4.31 |
ARIMA | 1791.37 | 1478.00 | 1063.89 | 1418.30 (+1422.61) |
ETS | 2431.82 | 2028.06 | 1246.41 | 1868.45 (+1872.76) |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 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
Thantharate, A.; Tondwalkar, A.V.; Beard, C.; Kwasinski, A. ECO6G: Energy and Cost Analysis for Network Slicing Deployment in Beyond 5G Networks. Sensors 2022, 22, 8614. https://doi.org/10.3390/s22228614
Thantharate A, Tondwalkar AV, Beard C, Kwasinski A. ECO6G: Energy and Cost Analysis for Network Slicing Deployment in Beyond 5G Networks. Sensors. 2022; 22(22):8614. https://doi.org/10.3390/s22228614
Chicago/Turabian StyleThantharate, Anurag, Ankita Vijay Tondwalkar, Cory Beard, and Andres Kwasinski. 2022. "ECO6G: Energy and Cost Analysis for Network Slicing Deployment in Beyond 5G Networks" Sensors 22, no. 22: 8614. https://doi.org/10.3390/s22228614