A reinforcement learning approach to dynamic resource allocation
نویسنده
چکیده
This paper presents a general framework for performing adaptive reconfiguration of a distributed system based on maximizing the long-term business value, defined as the discounted sum of all future rewards and penalties. The problem of dynamic resource allocation among multiple entities sharing a common set of resources is used as an example. A specific architecture (DRA-FRL) is presented, which uses the emerging methodology of reinforcement learning in conjunction with fuzzy rulebases to achieve the desired objective. This architecture can work in the context of existing resource allocation policies and learn the values of the states that the system encounters under these policies. Once the learning process begins to converge, the user can allow the DRA-FRL architecture to make some additional resource allocation decisions or override the ones suggested by the existing policies so as to improve the long-term business value of the system. The DRA-FRL architecture can also be deployed in an environment without any existing resource allocation policies. An implementation of the DRA-FRL architecture in Solaris 10 demonstrated a robust performance improvement in the problem of dynamically migrating CPUs and memory blocks between three resource partitions so as to match the stochastically changing ∗This material is based upon work supported by DARPA under Contract No. NBCH3039002.
منابع مشابه
Cycle Time Optimization of Processes Using an Entropy-Based Learning for Task Allocation
Cycle time optimization could be one of the great challenges in business process management. Although there is much research on this subject, task similarities have been paid little attention. In this paper, a new approach is proposed to optimize cycle time by minimizing entropy of work lists in resource allocation while keeping workloads balanced. The idea of the entropy of work lists comes fr...
متن کاملDynamic Resource Allocation through Reinforcement Learning Approach in Multi-cell OFDMA Networks
In this paper, we present a distributed resource allocation algorithm for cellular OFDMA networks by adopting a Reinforcement Learning (RL) approach. We use an RL method which employ Growing Self Organizing Maps to deal with the huge and continuous problem space. The goal of the algorithm is to maximize the network throughput in a fair manner. Indeed, the algorithm maximizes the throughput unti...
متن کاملMulticast Routing in Wireless Sensor Networks: A Distributed Reinforcement Learning Approach
Wireless Sensor Networks (WSNs) are consist of independent distributed sensors with storing, processing, sensing and communication capabilities to monitor physical or environmental conditions. There are number of challenges in WSNs because of limitation of battery power, communications, computation and storage space. In the recent years, computational intelligence approaches such as evolutionar...
متن کاملContributions to Efficient Resource Management in Virtual Networks
Network virtualisation is a promising technique for a better future Internet by allowing for network resource sharing. However, resource sharing requires that virtual nodes and links be embedded onto substrate nodes and links (virtual network embedding), and thereafter the allocated resources dynamically managed throughout the lifetime of the virtual network (dynamic resource allocation). Since...
متن کاملSvenson Stochastic dynamic programming for resource allocation
not more than 200 words) Resource allocation and management is an important part of the future network-based defence. In order to provide an adequate situation picture for commanders in the field, sensor platforms must be guided correctly and the needs of different users must be prioritized correctly. Other important problems which require resource allocation include determining where soldiers ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Eng. Appl. of AI
دوره 20 شماره
صفحات -
تاریخ انتشار 2007