Hyperspectral image (HSI) classification is an important task in the remote sensing community. In general, many hyperspectral classification methods are based on pixel patch, which leads to information redundancy. In this paper, we propose a multi-scale encoder-decoder network for HSI classification. First, we adapt an encoder-decoder framework as the backbone network and use a skip connection between the encoder and decoder, the spatial information is obtained by this network. Second, we develop a multi-scale block to get the multi-scale information. Third, we retain complete spectral information through the constant number of spectral channels. Finally, an optimizer strategy is designed to achieve our model for the HSI classification task. We experiment with our method and other methods on two public datasets, and the results denote our model is useful for HSI classification task.

Cloud computing has emerged as a new computing paradigm which has revolutionized the IT industry. It has particularly transformed the licensing of software products which are now being offered as a Service on pay-as-you-go basis. This has tremendously increased the complexity for software providers as they now have to not only manage their resources on which software are hosted but also they need to provide expected Quality of Service for customers. The Quality of Service (QoS) required by customers is guaranteed using a legal document SLA (Service Level Agreement). Current, resource management systems do not cater to the needs of a Software as a Service (SaaS) provider who requires to provide flexible and low cost services while not affecting their profit and market share. Most of them focus either at infrastructure level or at platform level. This work fills this gap by proposing a novel SLA based resource management system designed after analysing requirements of SaaS in Clouds. The proposed system is implemented using latest technologies and can scale in and out depending on updates in the user demand. We present the architectural design and evaluate the implementation with a real case study in a real Cloud environment.

Cloud computing is a solution for addressing challenges such as licensing, distribution, configuration, and operation of enterprise applications associated with the traditional IT infrastructure, software sales and deployment models. Migrating from a traditional model to the Cloud model reduces the maintenance complexity and cost for enterprise customers, and provides on-going revenue for Software as a Service (SaaS) providers. Clients and SaaS providers need to establish a Service Level Agreement (SLA) to define the Quality of Service (QoS). The main objectives of SaaS providers are to minimize cost and to improve Customer Satisfaction Level (CSL). In this paper, we propose customer driven SLA-based resource provisioning algorithms to minimize cost by minimizing resource and penalty cost and improve CSL by minimizing SLA violations. The proposed provisioning algorithms consider customer profiles and providers' quality parameters (e.g., response time) to handle dynamic customer requests and infrastructure level heterogeneity for enterprise systems. We also take into account customer-side parameters (such as the proportion of upgrade requests), and infrastructure-level parameters (such as the service initiation time) to compare algorithms. Simulation results show that our algorithms reduce the total cost up to 54 percent and the number of SLA violations up to 45 percent, compared with the previously proposed best algorithm.

A Service Level Agreement (SLA) is a legal contract between parties to ensure the Quality of Service (QoS) are provided the providers to the customers. A SLA negotiation between participants assists in defining the QoS requirements of critical service-based processes. However, the negotiation process for customers is a significant task particularly when there are multiple SaaS providers in the Cloud market, as service cost and quality are constantly changing and consumers have varying needs. Therefore, we propose a novel automated negotiation framework where a SaaS broker is utilized as the one-stop-shop for customers to achieve the required service efficiently when negotiating with multiple providers. The automated negotiation framework facilitates intelligent bilateral bargaining of SLAs between a SaaS broker and multiple providers to achieve different objectives for different participants. To maximize profit and improve customer satisfaction levels for the broker, we propose the design of counter offer generation strategies and decision making heuristics that take into account time, market constraints and trade-off between QoS parameters. Our negotiation heuristics are evaluated by extensive experimental studies of our framework using data from a real Cloud provider.

Cloud computing has been considered as a solution for solving enterprise application distribution and configuration challenges in the traditional software sales model. Migrating from traditional software to Cloud enables on-going revenue for software providers. However, in order to deliver hosted services to customers, SaaS companies have to either maintain their own hardware or rent it from infrastructure providers. This requirement means that SaaS providers will incur extra costs. In order to minimize the cost of resources, it is also important to satisfy a minimum service level to customers. Therefore, this paper proposes resource allocation algorithms for SaaS providers who want to minimize infrastructure cost and SLA violations. Our proposed algorithms are designed in a way to ensure that Saas providers are able to manage the dynamic change of customers, mapping customer requests to infrastructure level parameters and handling heterogeneity of Virtual Machines. We take into account the customers' Quality of Service parameters such as response time, and infrastructure level parameters such as service initiation time. This paper also presents an extensive evaluation study to analyze and demonstrate that our proposed algorithms minimize the SaaS provider's cost and the number of SLA violations in a dynamic resource sharing Cloud environment.

Cloud computing environments facilitate applications by providing virtualized resources that can be provisioned dynamically. However, users are charged on a pay-per-use basis. User applications may incur large data retrieval and execution costs when they are scheduled taking into account only the `execution time'. In addition to optimizing execution time, the cost arising from data transfers between resources as well as execution costs must also be taken into account. In this paper, we present a particle swarm optimization (PSO) based heuristic to schedule applications to cloud resources that takes into account both computation cost and data transmission cost. We experiment with a workflow application by varying its computation and communication costs. We compare the cost savings when using PSO and existing `Best Resource Selection' (BRS) algorithm. Our results show that PSO can achieve: (a) as much as 3 times cost savings as compared to BRS, and (b) good distribution of workload onto resources.