Mathematical programming approach for revenue maximization in cloud federations

Makhlouf Hadji (1, 2, 3) , Djamal Zeghlache (4, 1, 2, 3)

1 TSP - RS2M - Département Réseaux et Services Multimédia Mobiles
2 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
3 CNRS - Centre National de la Recherche Scientifique
4 R3S-SAMOVAR - Réseaux, Systèmes, Services, Sécurité

This paper assesses the benefits of cloud federation for cloud providers. Outsourcing and insourcing are explored as means to maximize the revenues of the providers involved in the federation. An exact method using a linear integer program is proposed to optimize the partitioning of the incoming workload across the federation members. A pricing model is suggested to enable providers to set their offers dynamically and achieve highest revenues. The conditions leading to highest gains are identified and the benefits of cloud federation are quantified

Mots clés: Optimization; Cloud federation; Resource allocation; Mathematical programming; Linear integer programming; Pricing

Domaines: Recherche opérationnelle [math.OC]; Réseaux et télécommunications [cs.NI]

Makhlouf Hadji, Djamal Zeghlache. Mathematical programming approach for revenue maximization in cloud federations. IEEE Transactions on Cloud Computing, 2017, 5 (1), pp.99 - 111. ⟨10.1109/TCC.2015.2402674⟩. ⟨hal-01462096⟩