In this paper, a Metascheduler architecture is proposed to be used on Cloud Computing environments. The aim of this Metascheduler architecture is to handle the submission of a service and to manage the infrastructure of the Grid resources belonging to the Cloud. Futhermore, this Metascheduler also aims of building the best pool of available resources for the implementation of the requests issued by a user. For this, an economy model based in approach of supply/demand is adopted. Additionally, it is proposed in this paper a novel approach for the communications between pairs of entities of the collaborative environment. This communications is implemented through the hierarchical P2P scheme, a model that extend the hierarchical model. The central idea on this model is the use of the upper level Metascheduler (named Superscheduler) to control partial overload and to impose performance under service demand.

Energy advancement and innovation have generated several challenges for large modernized cities, such as the increase in energy demand, causing the appearance of the small power grid with a local source of supply, called the Microgrid. A Microgrid operates either connected to the national centralized power grid or singly, as a power island mode. Microgrids address these challenges using sensing technologies and Fog-Cloudcomputing infrastructures for building smart electrical grids. A smart Microgrid can be used to minimize the power demand problem, but this solution needs to be implemented correctly so as not to increase the amount of data being generated. Thus, this paper proposes the use of Fog computing to help control power demand and manage power production by eliminating the high volume of data being passed to the Cloud and decreasing the requests’ response time. The GridLab-d simulator was used to create a Microgrid, where it is possible to exchange information between consumers and generators. Thus, to understand the potential of the Fog in this scenario, a performance evaluation is performed to verify how factors such as residence number, optimization algorithms, appliance shifting, and energy sources may influence the response time and resource usage.

The vast cloud computing environment holds out good prospects for researchers in the computing technology field. However, with several Cloud providers offering different pricing models, the evaluation and modeling of Cloud environments and applications are getting harder because there is a lack of tools for this task. We propose the CM Cloud Simulator to fill this gap since it provides a comprehensive and dynamic simulation of applications with various deployment configurations and incurs the cost it would require when implemented in a Cloud Provider, according to the cost model of any service provider. The CM Cloud Simulator also provides custom-built cost models through the XML file.

The number of surveillance cameras distributed over Smart Cities and the streaming workload generated by them have been increased. Although Fog computing has been used to reduce latency and jitter time, the gateways IoT may fail to collect information, producing missing or invalid data, affecting the quality of service. Therefore, this paper presents an analysis of gap filling algorithms to data missing problem in a smart surveillance environment. Performance Evaluation study has shown that it is possible to maximize the accuracy of data imputation using Singular Spectrum Analysis (SSA). SSA is characterized by time series field by performing a non-parametric spectral estimation with spatial-temporal correlations. Statistical outcomes have confirmed the requirement of accurate data imputation techniques to the Smart City environment, specifi¬cally in the surveillance scenario. In addition, the performance evaluation technique has allowed emphasizing the contribution of imputation data approaches. These approaches can estimate values that were not correctly monitored, increasing the accuracy in the estimation of the Streaming video, and thus improving the quality of service.

In the last 20 years, the amount of energy consumed has grown more than 50% and due to a shortage of energy resources in the future, will not be possible to meet all this demand. The current distribution model transports energy from stations to consumers, but does not consider the use of alternative sources. The smart grids have emerged to allow the inclusion of alternative forms of energy generation in the grid. Yet, to avoid an overload in the system is necessary to calculate the power flow in real time. In this paper, we use Fog Computing as mean to reduce the logical distance between the central distribution and consumption spot. IoT devices in the network edge have more effectiveness and less cost to handle the power flow information. We evaluate the performance of the Newton-Raphson and Gauss-Seidel algorithms with the objective of developing calculations in real time of the load flow problem with the help of fog. Our results have shown that is possible to make a smart grid based on Fog Computing and thus making smart electric networks that react to the environment.

Fault tolerance techniques can improve the trust of users in service oriented architectures as they can ensure data availability. This paper presents an implementation of a novel fault tolerance mechanism in a SOA architecture which simultaneously provides increased availability and better quality of service. In addition to this mechanism, a service selector using reputation ratings of the architecture components is discussed. The selection is based on information from past transactions of the components of the architecture, which allows to identify the best web services able to meet the requests of customers. The mechanisms are tested and a performance evaluation is presented to validate the results.