An Overview of IoT and Its Application With Machine Learning in Data Center

In the IoT system, captured plaintext data is sent to the cloud for storing, computing and further processing. But it is a potential concern to secure sensitive information like personal, financial, business, medical, etc. A certain number of researchers established IoT architecture with distinctive layers where data security is solely dependent on cloud service providers (CSPs) which make potential security threats. In this paper, an edge encryption support in the IoT architecture is implemented where the involvement of CSPs for security purposes becomes nullified. As the data become encrypted before it gets sent to the cloud, it becomes more secure and reliable for both the owner and shared users. Additionally, only the IoT node owner and shared users can access those data which provides better security, privacy, and control of data.

The Internet of Things (IoT) connects the things of our everyday life and supports us in our common activities. Several markets for IoT services have been created. These markets enable IoT users to search and compose services in order to support an IoT activity. However, existing IoT markets like IFTTT (If This Then That) are not convenient for users with respect to service discovery and composition. The objective of On-the-fly (OTF) computing is to configure and provide software markets that fulfill individual users' wishes by the automatic on-the-fly composition of single services. The architecture framework of On-the-fly computing markets helps architects to systematically develop these systems in different domains. In this paper, we use our OTF architectural framework to examine the requirements of a reference architecture for IoT markets. Furthermore, we perform a comparison between the architecture of IFTTT as an existing IoT market with this reference architecture. The results show how existing IoT markets can be improved. In return, the practical knowledge of IFTTT is taken to the reference architecture. This knowledge helps to overcome the limitations of today's IoT markets or creating new markets in the future.

Data centers are located centralized to do computation and accessing huge amount of data by the network devices which are interconnected to form the network path. Servers are stacked, data storage is placed in them. Data server backup and server redundancies are the recovery mechanisms implemented. Data centers compute, store, distribute the data by processing them and the data center controls all the interconnected network equipment in the distributed network. In current, RAID system is implemented to avoid the service disruptions due to disk failures, the availability of system and services are achieved with this expensive model. But still the availability is lost, and service disruptions happen due to disk failures, the machine learnings models to be used to predict the disk failures well in advance. Data center has increased usage of system with increased data storage, the failure in disc makes the system failed and down time increases. Analysis on the methods of problems in disk and methods of disk availability and predict the disk failure is the main goal. Various machine learning models are identified and discussed along with the SMART parameters for measuring the failure of the disk. Improved method of Ensembling of trees, random forest and boosting techniques are also discussed.