{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:38:53Z","timestamp":1760236733621,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T00:00:00Z","timestamp":1639612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Resource prediction algorithms have been recently proposed in Network Function Virtualization architectures. A prediction-based resource allocation is characterized by higher operation costs due to: (i) Resource underestimate that leads to quality of service degradation; (ii) used cloud resource over allocation when a resource overestimate occurs. To reduce such a cost, we propose a cost-aware prediction algorithm able to minimize the sum of the two cost components. The proposed prediction solution is based on a convolutional and Long Short Term Memory neural network to handle the spatial and temporal correlations of the need processing capacities. We compare in a real network and traffic scenario the proposed technique to a traditional one in which the aim is to exactly predict the needed processing capacity. We show how the proposed solution allows for cost advantages in the order of 20%.<\/jats:p>","DOI":"10.3390\/fi13120316","type":"journal-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T11:27:36Z","timestamp":1639654056000},"page":"316","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proposal and Investigation of a Convolutional and LSTM Neural Network for the Cost-Aware Resource Prediction in Softwarized Networks"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8480-8418","authenticated-orcid":false,"given":"Vincenzo","family":"Eramo","sequence":"first","affiliation":[{"name":"Department of Information Engineering, Electronic, Telecommunication, \u201cSapienza\u201d University of Rome, Via Eudossiana 18, 00184 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0220-8457","authenticated-orcid":false,"given":"Francesco","family":"Valente","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Electronic, Telecommunication, \u201cSapienza\u201d University of Rome, Via Eudossiana 18, 00184 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiziana","family":"Catena","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Electronic, Telecommunication, \u201cSapienza\u201d University of Rome, Via Eudossiana 18, 00184 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9565-8432","authenticated-orcid":false,"given":"Francesco Giacinto","family":"Lavacca","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Electronic, Telecommunication, \u201cSapienza\u201d University of Rome, Via Eudossiana 18, 00184 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1109\/COMST.2015.2477041","article-title":"Network Function Virtualization: State-of-the-art and Research Challenges","volume":"18","author":"Mijumbi","year":"2016","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1109\/LCOMM.2014.2360190","article-title":"Study of Migration Policies in Energy-Aware Virtual Router Networks","volume":"18","author":"Eramo","year":"2014","journal-title":"IEEE Commun. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4098","DOI":"10.1109\/JLT.2019.2921428","article-title":"Proposal and Investigation of a Reconfiguration Cost Aware Policy for Resource Allocation in Multi-Provider NFV Infrastructures Interconnected by Elastic Optical Networks","volume":"37","author":"Eramo","year":"2019","journal-title":"J. Light. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"44346","DOI":"10.1109\/ACCESS.2020.2978002","article-title":"Design and Implementation of Network-Aware VNF Migration Mechanism","volume":"8","author":"Yi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"200834","DOI":"10.1109\/ACCESS.2020.3035749","article-title":"Reconfiguration of Optical-NFV Network Architectures Based on Cloud Resource Allocation and QoS Degradation Cost-Aware Prediction Techniques","volume":"8","author":"Eramo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108104","DOI":"10.1016\/j.comnet.2021.108104","article-title":"Application of a Long Short Term Memory neural predictor with asymmetric loss function for the resource allocation in NFV network architectures","volume":"193","author":"Eramo","year":"2021","journal-title":"Comput. Netw."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Eramo, V., Lavacca, F.G., Catena, T., and Perez Salazar, P.J. (2020). Proposal and Investigation of an Artificial Intelligence (AI)-Based Cloud Resource Allocation Algorithm in Network Function Virtualization Architectures. Future Internet, 12.","DOI":"10.3390\/fi12110196"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Eramo, V., Valente, F., Lavacca, F.G., and Catena, T. (2021, January 4\u20138). Cost-Aware and AI-based Resource Prediction in Softwarized Networks. Proceedings of the 2021 AEIT International Annual Conference, Virtual.","DOI":"10.23919\/AEIT53387.2021.9626866"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Trakadas, P., Sarakis, L., Giannopoulos, A., Spantideas, S., Capsalis, N., Gkonis, P., Karkazis, P., Rigazzi, G., Antonopoulos, A., and Cambeiro, M.A. (2021). A Cost-Efficient 5G Non-Public Network Architectural Approach: Key Concepts and Enablers, Building Blocks and Potential Use Cases. Sensors, 21.","DOI":"10.3390\/s21165578"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9053","DOI":"10.1109\/ACCESS.2016.2639578","article-title":"Trade-Off Between Power and Bandwidth Consumption in a Reconfigurable Xhaul Network Architecture","volume":"4","author":"Eramo","year":"2016","journal-title":"IEEE Access"},{"key":"ref_11","unstructured":"Chiosi, M., Clarke, D., Feder, J., Cui, C., Benitez, J., Michel, U., Fumui, M., Delisle, D., Guardini, I., and Lopez, D. (2012). Network Functions Virtualization: An Introduction, Benefits, Enablers, Challenges and Call for Action, ETSI\u2014European Telecommunications Standards Institute. Technical Report."},{"key":"ref_12","unstructured":"ETSI Industry Specification Group (ISG) NFV (2021, November 15). ETSI Group Specifications on Network Function Virtualization. Available online: https:\/\/docbox.etsi.org\/ISG\/NFV\/Open\/Published\/."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s00607-021-00925-x","article-title":"Quality of service provisioning in network function virtualization: A survey","volume":"103","author":"Mostafavi","year":"2021","journal-title":"Computing"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"7368","DOI":"10.1007\/s11227-020-03502-9","article-title":"Algorithms for functionalities of virtual network: A survey","volume":"77","author":"Umrao","year":"2021","journal-title":"J. Supercomput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/TMC.2019.2942306","article-title":"Delay-Aware Virtual Network Function Placement and Routing in Edge Clouds","volume":"20","author":"Yang","year":"2021","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.comcom.2021.01.014","article-title":"A community detection based approach for Service Function Chain online placement in data center network","volume":"169","author":"Zu","year":"2021","journal-title":"Comput. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1109\/LCOMM.2020.3043845","article-title":"A Novel Approach for Service Function Chain Embedding in Cloud Datacenter Networks","volume":"25","author":"Qiao","year":"2021","journal-title":"IEEE Commun. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1109\/TNSM.2021.3055693","article-title":"Holu: Power-Aware and Delay-Constrained VNF Placement and Chaining","volume":"18","author":"Varasteh","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_19","unstructured":"Schneider, S., Puthenpurayil Satheeschandrany, N., Peuster, M., and Karl, H. (July, January 29). Machine Learning-Based Method for Prediction of Virtual Network Function Resource Demands. Proceedings of the 2020 IEEE Conference on Network Softwarization (NetSoft), Ghent, Belgium."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"D29","DOI":"10.1364\/JOCN.10.000D29","article-title":"Deep-Learning-Assisted Network Orchestration for On-Demand and Cost-Effective vNF Service Chaining in Inter-DC Elastic Optical Networks","volume":"10","author":"Li","year":"2018","journal-title":"IEEE J. Opt. Commun. Netw."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TPDS.2018.2867587","article-title":"Dynamic Network Function Instance Scaling Based on Traffic Forecasting and VNF Placement in Operator Data Centers","volume":"30","author":"Tang","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1109\/TNSM.2021.3055174","article-title":"An Adaptive Forecasting Model for Slice Allocation in Softwarized Networks","volume":"18","author":"Oliveira","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1109\/TCC.2016.2617374","article-title":"Energy-Aware VM Consolidation in Cloud Data Centers Using Utilization Prediction Model","volume":"7","author":"Farahnakian","year":"2019","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1007\/s11227-015-1426-8","article-title":"Multi-step-ahead Host Load Prediction using Autoencoder and Echo State Networks in Cloud Computing","volume":"71","author":"Yang","year":"2015","journal-title":"J. Supercomput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7592","DOI":"10.1007\/s11227-019-02967-7","article-title":"Host Load Prediction in Cloud Computing using Long Short-Term Memory Encoder-Decoder","volume":"75","author":"Nguyen","year":"2019","journal-title":"J. Supercomput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/TNSM.2021.3050955","article-title":"Centralized and Federated Learning for Predictive VNF Autoscaling in Multi-Domain 5G Networks and Beyond","volume":"18","author":"Subramanya","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2060","DOI":"10.1109\/LCOMM.2018.2864101","article-title":"Computing and Bandwidth Resource Allocation in Multi-Provider NFV Environment","volume":"22","author":"Eramo","year":"2018","journal-title":"IEEE Commun. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1109\/JLT.2003.808794","article-title":"Numerical Investigation on Design of Wide Geographical Optical Transport Networks Based on n\u00d7 40 Gbit\/s Transmission","volume":"21","author":"Matera","year":"2003","journal-title":"J. Light. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1109\/LCOMM.2003.813798","article-title":"Input Wavelength Conversion in Optical Packet Switches","volume":"7","author":"Eramo","year":"2003","journal-title":"IEEE Commun. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.comnet.2018.01.021","article-title":"A comprehensive survey of Network Function Virtualization","volume":"133","author":"Yi","year":"2018","journal-title":"Comput. Netw."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TSG.2017.2753802","article-title":"Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network","volume":"10","author":"Kong","year":"2019","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_32","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"Coursera Neural Netw. Mach. Learn."},{"key":"ref_33","unstructured":"(2021, November 15). EC2\u2014Amazon Web Services. Available online: https:\/\/aws.amazon.com\/ec2\/."},{"key":"ref_34","unstructured":"(2021, November 15). SND-lib. Available online: http:\/\/sndlib.zib.de\/home.action."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"105902","DOI":"10.1016\/j.ast.2020.105902","article-title":"Hybrid MultiGene Genetic Programming-Artificial neural networks approach for dynamic performance prediction of an aeroengine","volume":"103","author":"Quarta","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Brockwell, P.J., and Davis, R.A. (2016). Introduction to Time Series and Forecasting, Springer.","DOI":"10.1007\/978-3-319-29854-2"},{"key":"ref_37","unstructured":"(2021, November 15). KerasTuner. Available online: https:\/\/github.com\/keras-team\/keras-tuner."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/12\/316\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:50:07Z","timestamp":1760169007000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/12\/316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,16]]},"references-count":37,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["fi13120316"],"URL":"https:\/\/doi.org\/10.3390\/fi13120316","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2021,12,16]]}}}