Machine learning adaptive computational capacity prediction for dynamic resource management in C-RAN
Visualitza/Obre
10.1109/ACCESS.2020.2994258
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/327245
Tipus de documentArticle
Data publicació2020-05-23
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement 3.0 Espanya
ProjecteROBOTICA EN LA NUBE Y EL IMPACTO DE LAS REDES 5G EN LA FABRICA DEL FUTURO. SUBPROYECTO UPC. (AEI-RTI2018-099880-B-C32)
EC-CA15104-IRACON
EC-CA15104-IRACON
Abstract
Efficient computational resource management in 5G Cloud Radio Access Network (C-RAN)environments is a challenging problem because it has to account simultaneously for throughput, latency,power efficiency, and optimization tradeoffs. The assumption of a fixed computational capacity at thebaseband unit (BBU) pools may result in underutilized or oversubscribed resources, thus affecting the overallQuality of Service (QoS). As resources are virtualized at the BBU pools, they could be dynamically instan-tiated according to the required computational capacity (RCC). In this paper, a new strategy for DynamicResource Management with Adaptive Computational capacity (DRM-AC) using machine learning (ML)techniques is proposed. Three ML algorithms have been tested to select the best predicting approach: supportvector machine (SVM), time-delay neural network (TDNN), and long short-term memory (LSTM). DRM-AC reduces the average of unused resources by 96 %, but there is still QoS degradation when RCC is higherthan the predicted computational capacity (PCC). To further improve, two new strategies are proposed andtested in a realistic scenario: DRM-AC with pre-filtering (DRM-AC-PF) and DRM-AC with error shifting(DRM-AC-ES), reducing the average of unsatisfied resources by 98 % and 99.9 % compared to the DRM-AC, respectively
CitacióGuerra, R. [et al.]. Machine learning adaptive computational capacity prediction for dynamic resource management in C-RAN. "IEEE Access", 23 Maig 2020, vol. 8, núm. 1, p. 89130-89142.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
09091811final.pdf | 2,469Mb | Visualitza/Obre |