Makhlouf Hadji

Energy Efficient VM Scheduling for Cloud Data Centers: Exact Allocation and Migration Algorithms

This paper presents two exact algorithms for energy efficient scheduling of virtual machines (VMs) in cloud data centers. Modeling of energy aware allocation and consolidation to minimize overall energy consumption leads us to the combination of an optimal allocation algorithm with a consolidation algorithm relying on migration of VMs at service departures. The optimal allocation algorithm is solved as a bin packing problem with a minimum power consumption objective. It is compared with an energy aware best fit algorithm. The exact migration algorithm results from a linear and integer formulation of VM migration to adapt placement when resources are released. The proposed migration is general and goes beyond the current state of the art by minimizing both the number of migrations needed for consolidation and energy consumption in a single algorithm with a set of valid inequalities and conditions. Experimental results show the benefits of combining the allocation and migration algorithms and demonstrate their ability to achieve significant energy savings while maintaining feasible convergence times when compared with the best fit heuristic.

Minimum Cost Maximum Flow Algorithm for Dynamic Resource Allocation in Clouds

A minimum cost maximum flow algorithm is proposed for resources(e.g. virtual machines) placement in clouds confronted to dynamic workloads and flows variations. The algorithm is compared to an exact method generalizing the classical Bin-Packing formulation using a linear integer program. A directed graph is used to model the allocation problem for cloud resources organized in a finite number of resource types; a common practice in cloud services. Providers can use the minimum cost maximum flow algorithm to opportunistically select the most appropriate physical resources to serve applications or to ensure elastic platform provisioning. The modified Bin-Packing algorithm is used to benchmark the minimum cost maximum flow solution. The latter combined with a prediction mechanism to handle dynamic variations achieves near optimal performance.

Improving profit through cloud federation

This paper addresses profit optimization through insourcing and outsourcing virtual resources (seen as VMs) for cloud infrastructure providers. A linear program is proposed to assist IaaS providers, involved in a cloud federation, in adjusting their hosting and cooperation decisions in response to their workloads and available resources. The proposed exact formulation takes into account the prices and quotas proposed by the federation members and the costs of resources and their networking to maximize providers revenues. The algorithm performance evaluation and the identified benefits show the conditions for profitable cloud federations and the efficiency of the proposed model in improving profit.

Exact and Heuristic Resource Mapping Algorithms for Distributed and Hybrid Clouds

This paper addresses the problem of cloud and networking resources mapping in distributed and hybrid cloud environments. In this context private and public resources are acquired and combined to set up tenant dedicated virtual infrastructures to fulfil distributed applications requirements. An exact algorithm is proposed to map jointly nodes and links of the requested virtual infrastructure graph to the physical graph from multiple providers (data centers and network providers). We view the problem as a virtual network mapping and use integer linear programming to find optimal solutions. To address complexity and scalability for large virtual and physical networks of thousands of nodes, an efficient heuristic algorithm, relying on topology patterns and bipartite matching, is used to provide close to optimal solutions and reduce mapping delays by three to four orders of magnitude.

Scalable and Cost Efficient Algorithms for Virtual CDN Migration

Virtual Content Delivery Network (vCDN) migration is necessary to optimize the use of resources and improve the performance of the overall SDN/NFV-based CDN function in terms of network operator cost reduction and high streaming quality. It requires intelligent and enticed joint SDN/NFV migration algorithms due to the evident huge amount of traffic to be delivered to end customers of the network. In this paper, two approaches for finding the optimal and near optimal path placement(s) and vCDN migration(s) are proposed (OPAC and HPAC). Moreover, several scenarios are considered to quantify the OPAC and HPAC behaviors and to compare their efficiency in terms of migration cost, migration time, vCDN replication number, and other cost factors. Then, they are implemented and evaluated under different network scales. Finally, the proposed algorithms are integrated in an SDN/NFV framework.

Scalable and cost-efficient algorithms for VNF chaining and placement problem

This paper focuses on placement and chaining of virtualized network functions (VNFs) in Network Function Virtualization Infrastructures (NFVI) for emerging software networks serving multiple tenants. Tenants can request network services to the NFVI in the form of service function chains (in the IETF SFC sense) or VNF Forwarding Graphs (VNF-FG in the case of ETSI) in support of their applications and business. This paper presents efficient algorithms to provide solutions to this NP-Hard chain placement problem to support NFVI providers. Cost-efficient and improved scalability multi-stage graph and 2-Factor algorithms are presented and shown to find near-optimal solutions in few seconds for large instances.

A novel virtual network embedding scheme based on Gomory-Hu tree within cloud's backbone

We address the online virtual network embedding problem within the Clouds backbone to optimally map the virtual routers and links in the substrate network in order to maximize the Clouds provider revenue. Since the problem is NP-hard, we propose a novel approach, named VNE-GH, to significantly reduce the problem size using the Gomory-Hu transformation without losing useful information on the virtual network embedding problem. Starting from the Gomory-Hu compact tree structure, we formulate the virtual network embedding as an Integer Linear Program and resolve the reduced size problem using the branch- and-cut algorithm. Results obtained via extensive simulations show that VNE-GH outperforms the most prominent related work strategies in terms of i) acceptance rate of virtual network requests and ii) Cloud providers revenue.

Designing Steiner Networks with Unicyclic Connected Components: An Easy Problem

This paper focuses on the design of minimum-cost networks satisfying two technical constraints. First, the connected components should be unicyclic. Second, some given special nodes must belong to cycles. This problem is a generalization of two known problems: the perfect binary 2-matching problem and the problem of computing a minimum-weight basis of the bicircular matroid. It turns out that the problem is polynomially solvable. An exact extended linear formulation is provided. We also present a partial description of the convex hull of the incidence vectors of these Steiner networks. Polynomial-time separation algorithms are described. One of them is a generalization of the Padberg-Rao algorithm to separate blossom inequalities.

IoT_ProSe: Exploiting 3GPP services for task allocation in the Internet of Things

Abstract This work focuses on the problem of task allocation among mobile objects that aim to collaborate in the execution of IoT (Internet of Things) applications. We consider 3GPP Proximity Services (ProSe) that enable Device to Device (D2D) communications for direct interaction among IoT objects. We first define the framework where devices willing to cooperate: (i) discover and join a cluster of objects to take part to the IoT_ProSe service; (ii) compete with the other objects in the cluster when a request for a service is sent to the cluster from the IoT application server. We then focus on two important problems. The first problem is the decision about which node should win the competition, for which we propose a game-theory based approach to find a solution maximizing objects’ utility functions. The second problem is the computation of the optimal size of devices’ clusters within a cell by maximizing the signal quality across the cell. Experimental results provide insights on the strategy performance. By appropriately setting working parameters, it is possible to improve system reliability up to 21%, and system lifetime up to 68%.

Virtualized network functions chaining and routing algorithms

Abstract We focus on the placement of Virtualized Network Functions (VNFs) chains in the Network Function Virtualization (NFV) context where NFV Infrastructures (NFVIs) are used to host the VNFs. The optimal placement of VNF (service) chains in hosting infrastructures is one of the key issues in the deployment of service functions in large-scale environments. The Virtualized Network Functions Chain Placement Problem VNF-CPP is NP-Hard and there is a need for placement approaches that can scale with problem size and find good solutions in acceptable times. We propose a matrix-based optimization and a multi-stage graph method that are cost efficient and improve scalability by finding solutions in polynomial times. These algorithms are compared with an exact formulation given by the Perfect 2-Matching leading to a polynomial variant of the VNF-CPP for VNF chains with 2 arcs. Simulation results for longer and more complex chains confirm the efficiency and scalability of the proposed methods and their ability to find good suboptimal solutions.