Algorithms for efficient data management of component-based applications in cloud environments

Barshan, Maryam; Moens, Hendrik; Latré, Steven; Turck, Filip De

doi:10.1109/noms.2014.6838257

Cited by 16 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case the algorithm must backtrack and start again with new default servers and continue until the NSS process is unable to find a new server. This algorithm differs from our previously designed algorithm in [13] because in this paper the next server is found by calling the BFS algorithm, whereas in the previous work the process searches among the neighbours and in the case of no unvisited neighbour another arbitrary server was chosen, an approach which is less efficient for large-scale networks.…”

Section: A Centralized Cloud Mapping Algorithm (Ccma)mentioning

confidence: 99%

“…Nevertheless, this work differs from our approach as it is centralized and not network-aware. In our previous work [13] we presented an optimal ILPbased solution with the main focus of cost-effectiveness along with a central heuristic algorithm. This algorithm is however centralized, making it only useful for smaller datacenters.…”

Section: Related Workmentioning

confidence: 99%

“…First an evaluation of the CCMA is provided by comparing to an optimal solution based on the ILP-based model we presented in [13]. Then, we evaluate the HCMA by comparing its performance with the CCMA.…”

Section: Evaluation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Design and evaluation of a scalable hierarchical application component placement algorithm for cloud resource allocation

Barshan

Moens

Turck

2014

10th International Conference on Network and Service Management (CNSM) and Workshop

Self Cite

View full text Add to dashboard Cite

Abstract-In the context of cloud systems, mapping application components to a set of physical servers and assigning resources to those components is challenging. For large-scale clouds, traditional resource allocation systems, which rely on a centralized management paradigm, become ineffective and inefficient. Therefore, there is an essential need of providing new management solutions that scale well with the size of large cloud systems. In this paper a distributed and hierarchical component placement algorithm is presented, evaluated and compared to a centralized algorithm. Each application is represented as a collection of interacting services, and multiple service types with differing placement characteristics are considered. Our evaluations show that the proposed algorithm is at least 84.65 times faster and offers better scalability compared with a central approach, while the percentage of servers used and fully placed applications remains close to that of the centralized algorithm.

show abstract

Section: A Centralized Cloud Mapping Algorithm (Ccma)mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Design and evaluation of a scalable hierarchical application component placement algorithm for cloud resource allocation

Barshan

Moens

Turck

2014

10th International Conference on Network and Service Management (CNSM) and Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…The VNF placement and the datacenters/clouds component placement are conceptually similar. A number of studies have been published in this domain . A survey on resource management in cloud computing environments is presented by Jennings and Stadler .…”

Section: Related Workmentioning

confidence: 99%

“…In order to address the scalability problem of centralized algorithms, the authors propose a distributed algorithm that achieves performance similar to the one of centralized algorithms. The authors then extend their work by proposing several algorithms aiming at efficiently managing data of component‐based applications. Ghaznavi et al jointly considers the trade‐offs between bandwidth and host resource consumption, and the elasticity overhead in the VNF placement problem formulation.…”

Section: Related Workmentioning

confidence: 99%

CU placement over a reconfigurable wireless fronthaul in 5G networks with functional splits

et al. 2019

View full text Add to dashboard Cite

Mobile network operators are currently facing a tremendous increase in the level of data traffic. Although cell size reduction is one of the most common ways used to accommodate such traffic demand, densely deployed small cells also dramatically increase the level of intercell interference. By centralizing baseband signal processing at powerful computing infrastructures, called centralized unit (CU) pools, cloud radio access network (C-RAN) enables advanced coordination algorithms to be employed in dense small cell networks. In C-RAN, due to stringent bandwidth and latency requirements at the fronthaul links, the optical fiber, thanks to its bandwidth and latency characteristics, continues to be the most prevalent fronthaul medium option. Nevertheless, the optical fiber is one of the fronthaul options, while C-RAN (physical layer radio frequency [PHY-RF] split) is one of the functional splits that can be defined each coming with different fronthaul requirements.In this paper, we formulate and solve a dynamic CU placement problem for mobile networks as an integer linear programming (ILP) problem. In the considered network, CU pools are placed at the edges of the network, and a reconfigurable millimeter wave (MMW) wireless fronthaul links are used in order to provide decentralized units (DUs) with connectivity. We study the impact of different functional splits on the placement cost and on the acceptance ratio using different substrate networks. Lastly, we propose and evaluate a CU placement heuristic algorithm using a numerical simulator. The results reveal that the optimal functional split selection can lead to significant resource utilization benefits in the RAN.Int J Network Mgmt. 2020;30:e2086. wileyonlinelibrary.com/journal/nem to the distributed radio access network (D-RAN) architecture, in which coaxial cables are substituted by optical fibers, and a digital interface is used to carry the in-phase/quadrature (I/Q) samples between the baseband unit and the radio unit. However, since in the D-RAN architecture a Long-Term Evolution (LTE) base station, called eNB, cannot share its frequency resources with other eNBs. These scarce frequency resources will be underutilized most of the time in a day due to the spatiotemporally fluctuating traffic demand. In order to tackle the aforementioned problem, the cloud RAN (C-RAN) 3 architecture has been recently proposed. C-RAN is capable of reducing the total cost of ownership (TCO) of mobile networks while, at the same time, optimizing network capacity, coverage, and power consumption. Such goals are achieved in C-RAN by separating baseband units, termed centralized units (CUs) from the radio units, termed distributed units (DUs) and combining CUs in powerful computing infrastructures, termed CU pools. * CU pools can run on a number of general-purpose of-the-shelf servers deployed in centralized locations.The separation of the signal processing functionalities in the RAN protocol stack between the CU pool and the DU is known as functional split. 5 Traditionally, in the ...

show abstract

Dynamic process location management in 5G

Vakilinia

Elbiaze²

2019

Int J Communication

View full text Add to dashboard Cite

Summary5G, as the next generation of wireless networks, promises very high throughput and low latency to mobile users that calls for a substantial innovation in computing management platforms to attend QoS metrics. Thanks to emerging technologies such as software‐defined networking (SDN)/network function virtualization (NFV), many features are available in 5G design to detect and control two types of latency caused by computation and communication.In this paper, taking features of caching mechanisms and SDN into the account, a platform is proposed to minimize latency in 5G via caching big flows intelligently and avoiding bottlenecks that may cause by virtualized computing components. First, the pioneering idea of compromising between the cloud radio access network (CRAN) and mobile edge computing (MEC)/information‐centric network (ICN) via dynamic processing location management platform is investigated. Accordingly, a mathematical optimization problem to minimize the average latency is formulated. Due to the problem complexity, a heuristic algorithm is proposed to treat the latency via dynamic orchestration of processing functionalities. Through numerical results, the performance of the proposed algorithm is analyzed, and the simulations corroborate our analytical results and illustrate the superior performance of the proposed algorithm with acceptable optimality gap.

show abstract

Algorithms for efficient data management of component-based applications in cloud environments

Cited by 16 publications

References 15 publications

Design and evaluation of a scalable hierarchical application component placement algorithm for cloud resource allocation

Design and evaluation of a scalable hierarchical application component placement algorithm for cloud resource allocation

CU placement over a reconfigurable wireless fronthaul in 5G networks with functional splits

Dynamic process location management in 5G

Contact Info

Product

Resources

About