Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReproducible experiments on dynamic resource allocation in cloud data centers
103
0
0.0
(
0
)
Added by
Vicky Steeves
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In Wolke et al. [1] we compare the efficiency of different resource allocation strategies experimentally. We focused on dynamic environments where virtual machines need to be allocated and deallocated to servers over time. In this companion paper, we describe the simulation framework and how to run simulations to replicate experiments or run new experiments within the framework.
rate research
Read More
Artificial Intelligence (AI) and Internet of Things (IoT) applications are rapidly growing in todays world where they are continuously connected to the internet and process, store and exchange information among the devices and the environment. The cloud and edge platform is very crucial to these applications due to their inherent compute-intensive and resource-constrained nature. One of the foremost challenges in cloud and edge resource allocation is the efficient management of computation and communication resources to meet the performance and latency guarantees of the applications. The heterogeneity of cloud resources (processors, memory, storage, bandwidth), variable cost structure and unpredictable workload patterns make the design of resource allocation techniques complex. Numerous research studies have been carried out to address this intricate problem. In this paper, the current state-of-the-art resource allocation techniques for the cloud continuum, in particular those that consider time-sensitive applications, are reviewed. Furthermore, we present the key challenges in the resource allocation problem for the cloud continuum, a taxonomy to classify the existing literature and the potential research gaps.
This volume represents the proceedings of the 2nd International Workshop on Dynamic Resource Allocation and Management in Embedded, High Performance and Cloud Computing (DREAMCloud 2016), co-located with HiPEAC 2016 on 19th January 2016 in Prague, Czech Republic.
To ensure uninterrupted services to the cloud clients from federated cloud providers, it is important to guarantee an efficient allocation of the cloud resources to users to improve the rate of client satisfaction and the quality of the service provisions. It is better to get as more computing and storage resources as possible. In cloud domain several Multi Agent Resource Allocation methods have been proposed to implement the problem of dynamic resource allocation. However the problem is still open and many works to do in this field. In cloud computing robustness is important so in this paper we focus on auto-adaptive method to deal with changes of open federated cloud computing environment. Our approach is hybrid, we first adopt an existing organizations optimization approach for self organization in broker agent organization to combine it with already existing Multi Agent Resource Allocation approach on Federated Clouds. We consider an open clouds federation environment which is dynamic and in constant evolution, new cloud operators can join the federation or leave this one. At the same time our approach is multi criterion which can take in account various parameters (i.e. computing load balance of mediator agent, geographical distance (network delay) between costumer and provider...).
Blockchain assisted federated learning (BFL) has been intensively studied as a promising technology to process data at the network edge in a distributed manner. In this paper, we focus on BFL over wireless environments with varying channels and energy harvesting at clients. We are interested in proposing dynamic resource allocation (i.e., transmit power, computation frequency for model training and block mining for each client) and client scheduling (DRACS) to maximize the long-term time average (LTA) training data size with an LTA energy consumption constraint. Specifically, we first define the Lyapunov drift by converting the LTA energy consumption to a queue stability constraint. Then, we construct a Lyapunov drift-plus-penalty ratio function to decouple the original stochastic problem into multiple deterministic optimizations along the time line. Our construction is capable of dealing with uneven durations of communication rounds. To make the one-shot deterministic optimization problem of combinatorial fractional form tractable, we next convert the fractional problem into a subtractive-form one by Dinkelbach method, which leads to the asymptotically optimal solution in an iterative way. In addition, the closed-form of the optimal resource allocation and client scheduling is obtained in each iteration with a low complexity. Furthermore, we conduct the performance analysis for the proposed algorithm, and discover that the LTA training data size and energy consumption obey an [$mathcal{O}(1/V)$, $mathcal{O}(sqrt{V})$] trade-off. Our experimental results show that the proposed algorithm can provide both higher learning accuracy and faster convergence with limited time and energy consumption based on the MNIST and Fashion-MNIST datasets.
With the development of federated learning (FL), mobile devices (MDs) are able to train their local models with private data and sends them to a central server for aggregation, thereby preventing sensitive raw data leakage. In this paper, we aim to improve the training performance of FL systems in the context of wireless channels and stochastic energy arrivals of MDs. To this purpose, we dynamically optimize MDs transmission power and training task scheduling. We first model this dynamic programming problem as a constrained Markov decision process (CMDP). Due to high dimensions rooted from our CMDP problem, we propose online stochastic learning methods to simplify the CMDP and design online algorithms to obtain an efficient policy for all MDs. Since there are long-term constraints in our CMDP, we utilize Lagrange multipliers approach to tackle this issue. Furthermore, we prove the convergence of the proposed online stochastic learning algorithm. Numerical results indicate that the proposed algorithms can achieve better performance than the benchmark algorithms.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
