Real Traffic-Aware Scheduling of Computing Resources in Cloud-RAN

Khedher, Hatem Ibn; Hoteit, Sahar; Brown, Patrick; Krishnaswamy, Ruby; Diego, William; Hadji, Makhlouf

doi:10.1109/icnc47757.2020.9049679

Cited by 5 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We assume that the radio scheduling, the PHY layer and the lower MAC layer work as in LTE. Let N be the set of the RHs, which we assume operate in the 20 MHz bandwidth, so that the number of physical resource blocks per subframe is 100 [12], [14], for all RH. We assume that each subframe carries data of a single user and uses only one MCS.…”

Section: System Setup and Problem Definitionmentioning

confidence: 99%

“…When a MAC message is generated it is associated with an MCS, which is constant for all HARQ transmissions. For MCS sampling we use, as in [14], an empirical distribution evaluated from the data set in [16]. The data set [16] records real traffic in 4 mobile cells and reports the MCS occurrence.…”

Section: A Mcs Samplingmentioning

confidence: 99%

“…This formulation has already been explored in [14], where the optimization problem is expressed as follows:…”

Section: Resource Allocation As An Optimization Problemmentioning

confidence: 99%

“…We model these events as packet losses at PHY layer. The computing resource allocation algorithms found in the literature generally aim to minimize the packet loss rate [9], [14], which is a very natural choice.…”

Section: Introductionmentioning

confidence: 99%

“…The system and simulations setups are described in detail in Sections II and III, respectively. The allocation policy that minimizes the PHY packet losses is formulated as an Integer Linear Program [14] in Section IV, where we turn it in a cross-layer policy by incorporating the HARQ retransmission age of the message in the objective function. This achieves a consistent improvement in the BER, for the same Goodput, at the expense of the average delay.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

HARQ-aware allocation of computing resources in C-RAN

Bassi

Khedher

2020

2020 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

The principal tenet of C-RAN is the softwarization of the base-band signal processing, which enables the sharing of computing resources among multiple radio heads. When the aggregate demand exceeds the processing capacity, a fraction of the radio packets is lost at PHY layer. Traditional computing resource allocation policies aim to minimize the packet loss rate.Dropping a PHY packet triggers a retransmission, unless the lost packet corresponds to the last available HARQ round, in which case the entirety of the radio resources spent on the multiple transmissions go to waste. This suggests that allocating computing resource accounting also for the HARQ transmission history may make a more efficient use of the bandwidth.We consider a simplified LTE uplink setting, and we measure the performance at the lower MAC layer (accuracy, goodput and average delay). We first compare the PHY-layer loss rate minimization and the cross-layer approaches using an ILP formulation. The cross-layer approach brings a tangible improvement, especially in accuracy. This suggests, for future work, that joint radio and computing resource allocation may further enhance spectral efficiency. We finally propose a probabilistic algorithm amenable to real-time operation which allows to mix strategies via parameter tuning, and we use it to explore the region of achievable goodput/accuracy trade-offs.

show abstract

Section: System Setup and Problem Definitionmentioning

confidence: 99%

Section: A Mcs Samplingmentioning

confidence: 99%

“…This formulation has already been explored in [14], where the optimization problem is expressed as follows:…”

Section: Resource Allocation As An Optimization Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

HARQ-aware allocation of computing resources in C-RAN

Bassi

Khedher

2020

2020 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

show abstract

Globally Optimal Resource Allocation and Time Scheduling in Downlink Cognitive CRAN Favoring Big Data Requests

et al. 2022

View full text Add to dashboard Cite

This paper is concerned with a cognitive cloud radio access network (CRAN) with a special attention to efficient and reliable transmission of big data. In particular, the paper focuses on optimizing performance of secondary users (SUs) in the downlink. Existing approaches either try to maximize the number of accepted SUs or the sum data rate of accepted SUs. The first approach unfairly favors users with small data requests, whereas the second approach allocates most resources to users with better channel conditions. In contrast, this paper develops a novel approach that favors big data requests while simultaneously maintaining a certain degree of fairness among SUs. To this end, we first introduce a novel objective function that allows us to jointly optimize deadline-aware time scheduling, spectrum allocation, SU selection, and remote radio head (RRH) allocation for SUs. Second, we demonstrate that finding the global optimum solution for the formulated problem entails the enumeration of all colorful independent sets on a generalized interval graph which is known to be NP-hard. Third, we propose a dynamic programming (DP) approach which yields the global optimum solution at a reduced computational cost. Fourth, we analyze the complexity of the proposed DP approach and numerically compare its performance against existing baseline algorithms. Numerical and simulation results revealed that our solution favors big data users while incurring only a small degradation in the fairness index. Our proposed solution is practical for small-to-medium size networks. Furthermore, it offers a benchmark against which any new sub-optimal low-complexity algorithm can be compared to determine how far from the global optimum its performance is.

show abstract

A Recurrent Neural Network Based Approach for Coordinating Radio and Computing Resources Allocation in Cloud-RAN

Sharara

Hoteit

2021

2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR)

Self Cite

View full text Add to dashboard Cite

Cloud Radio Access Network (Cloud-RAN) is a novel architecture that aims at centralizing the baseband processing of base stations. This architecture opens paths for joint, flexible, and optimal management of radio and computing resources. To increase the benefit from this architecture, efficient resource management algorithms need to be devised. In this paper, we consider a coordinated allocation of radio and computing resources to mobile users. Optimal resource allocation that respects the Hybrid-Automatic-Repeat-Request deadline may require formulating high-complexity and resourceheavy algorithms. We consider two Integer Linear Programming problems (ILP) that implement a coordinated allocation of radio and computing resources with the objectives of maximizing throughput and maximizing users' satisfaction, respectively. Since solving these highly-complex problems requires a high execution time, we investigate low-complexity alternatives based on machine learning models; more precisely on Recurrent Neural Networks (RNN). These RNN models aim to depict the performance of the ILP problems with a much lower execution time. Our simulation results demonstrate the great ability of RNN models to perform very closely to the ILP problems while being able to reduce the execution time by up to 99.65%.

show abstract

Real Traffic-Aware Scheduling of Computing Resources in Cloud-RAN

Cited by 5 publications

References 9 publications

HARQ-aware allocation of computing resources in C-RAN

HARQ-aware allocation of computing resources in C-RAN

Globally Optimal Resource Allocation and Time Scheduling in Downlink Cognitive CRAN Favoring Big Data Requests

A Recurrent Neural Network Based Approach for Coordinating Radio and Computing Resources Allocation in Cloud-RAN

Contact Info

Product

Resources

About