Article Preview
TopBackground
This section presents the previous work done by academicians and Industria.
The authors have proposed framework named as SOOTER which provides the self-management of resources. During self-provisioning of resources, the authors maintained the SLA and maximum possibility of QoS parameter. The proposed architecture has been divided into two phases: - Resource Provisioning and Resource Scheduling. In resource provision phase the RPA has the responsibility to analysis the workload, SLA and QoS. Further this information has to forwarded in second phase for resource monitoring and assigns resources to available VM (Gill et al, (2019)).
In this, the authors have proposed that monarch butterflies can be detected individually and can be found in Northern US and Mexico and South Canada. Here, South Canada is considered as Land1 and Mexico is considered as Land2. However, the final location is updated in two steps i.e., migration operator and other is adjusting operator. Both the operators can work simultaneously. This MBO is suitable for parallel processing. Finally, the MBO algorithm implements the exploitation and exploration by utilizing various solution to VM migration and other adjusting operators (Alweshah et al, (2020)).
In this, the author presented a novel security-guaranteed picture watermarking generation scenario based on CNN for smart city software. The content-based watermark synchronization scheme defines watermark embedding locations using secure image feature points in the existing anti-geometric attack watermarking algorithm, integrates the watermark in a nearby neighborhood feature point, and detects the watermark using the key points. Therefore, the robustness feature is proved by this point. To define the path information for each feature point, the gradient direction distribution of the adjacent pixels of a feature point is used. In reality, in a neighborhood window based on the feature points, sampling is done and a histogram is used to measure the gradient directions of the adjacent pixels. At the feature point, that is, the main direction of the feature point, the peak of the histogram represents the primary direction of the neighborhood gradient (Li et al, (2019)).