Nantilus
Dynamic Pricing and Automated Resource Allocation for Complex Information Services : Reinforcement Learning and Combinatorial Auctions
Many firms provide their customers with online information products which require limited resources such as server capacity. This book develops allocation mechanisms that aim to ensure an efficient resource allocation in modern IT-services. Recent methods of artificial intelligence, such as neural n...
Enregistré dans:
| Auteur principal : | |
|---|---|
| Format : | Livre |
| Langue : | anglais |
| Titre complet : | Dynamic Pricing and Automated Resource Allocation for Complex Information Services : Reinforcement Learning and Combinatorial Auctions / by Michael Schwind. |
| Édition : | 1st ed. 2007. |
| Publié : |
Berlin, Heidelberg :
Springer Berlin Heidelberg
, 2007 |
| Collection : | Lecture notes in economics and mathematical systems (Internet) ; 589 |
| Accès en ligne : |
Accès Nantes Université
Accès direct soit depuis les campus via le réseau ou le wifi eduroam soit à distance avec un compte @etu.univ-nantes.fr ou @univ-nantes.fr |
| Contenu : | Dynamic Pricing and Automated Resource Allocation. Empirical Assessment of Dynamic Pricing Preference. Reinforcement Learning for Dynamic Pricing and Automated Resource Allocation. Combinatorial Auctions for Resource Allocation. Dynamic Pricing and Automated Resource Allocation Using Combinatorial Auctions. Comparison of Reinforcement Learning and Combinatorial Auctions |
| Sujets : | |
| Documents associés : | Autre format:
Dynamic Pricing and Automated Resource Allocation for Complex Information Services Autre format: Dynamic pricing and automated resource allocation for complex information services |
| Résumé : | Many firms provide their customers with online information products which require limited resources such as server capacity. This book develops allocation mechanisms that aim to ensure an efficient resource allocation in modern IT-services. Recent methods of artificial intelligence, such as neural networks and reinforcement learning, and nature-oriented optimization methods, such as genetic algorithms and simulated annealing, are advanced and applied to allocation processes in distributed IT-infrastructures, e.g. grid systems. The author presents two methods, both of which using the users willingness-to-pay to control the allocation process: The first approach uses a yield management method that tries to learn an optimal acceptance strategy for resource requests. The second method is a combinatorial auction able to deal with resource complementarities. The author finally generates a method to calculate dynamic resource prices, marking an important step towards the industrialization of grid systems |
|---|---|
| Configuration requise : | Nécessite un lecteur de fichier PDF |
| ISBN : | 978-3-540-68003-1 |