IOT ENABLED SECURED FOG BASED CLOUD SERVER MANAGEMENT USING TASK PRIORITIZATION STRATEGIES

Internet of Things (IoT) enabled services are the major and prominent need over the information technology industry. IoT environment provide services to present technology devices to make a global communication without any region or locationbased restrictions. The data from anywhere in the globe can easily be communicated to the remote server without any boundary limitations by using this IoT services. This is the reason most of the companies and firms trying to accumulate the benefits of this IoT services. The remote server is nothing but a Cloud environment, in which the data to be stored in the remote place for processing, instead of that to maintain in the local space. The cloud computing strategies are most admirable to all fields for handling the data in more secure manner over the remote place by using cloud default crypto strategies. This paper consider all these benefits and provide an excellent solution to the organizations to manage all required information over cloud environment without any flaws and problems. In this paper, various technology adaptations are blended together and provide a unique solution to data management process, the technologies handled over this paper are: IoT, Cloud Computing, Machine Learning and Fog Services. The concept of IoT is used to collect the data from locally placed sensor and pushing all the data to remote cloud server vice versa collect the data from remote server and manipulate that into local device operations if necessary. The cloud computing process are required to collect the data from IoT devices and stored those into the server, in which the Task Prioritization logic is applied in this paper to evaluate the prioritized tasks and pushing that into the remote cloud server, remaining non-prioritized data to be maintained into the fog environment. This is achieved by using machine learning strategies, in which the algorithm of Artificial Neural network is used over this approach to task manipulations. The concept of squirrel optimization algorithm is obtained in this proposed approach to perform efficient searching schemes to retrieve the data from cloud environment. A Local Search establishment scheme allows the system to search for the data based on its features and retrieve the respective results from server based on the feature selection process. The concept of Squirrel Optimization algorithm and the Local Search optimization algorithm is efficiently used in this proposed approach for generating the priority token to the classification algorithm, by means of analyzing the present data from IoT sensors to the already trained data over the server. The data presented in the remote cloud server will be analyzed by using Squirrel Optimization algorithm and the local fog data is analyzed by using Local Search Optimization algorithm. These two algorithms are operating in hybrid manner to generate the priority token based on the trained data availability over cloud and the resulting priority token is provided to the ANN algorithm for classification process, based on the priority token the classification algorithm operates and provide the perfect outcome. This process of task prioritization assures the reduction over cloud traffic scenarios and provides higher searching as well as processing efficiency. The fog computing principles are established in this approach to maintain the non-prioritized records received from IoT sensors/devices. The proposed paper assures the cost efficient and secured task prioritization process over cloud environment using machine learning principles.