Rezanov B. Models and methods for optimizing task distribution in the Fog environment of the Internet of Things

The dissertation work is devoted to solving an urgent scientific and technical problem related to the development of new and improvement of existing methods for distributing tasks that need to be performed in near real time in foggy environments of the Internet of Things. Object of research is the process of task distribution in the foggy environment of the Internet of Things. The subject of research is models and methods of task distribution in the foggy environment of the Internet of Things. The purpose of the dissertation is to increase the efficiency of using the computing resources of the foggy environments of the Internet of Things by developing new and improving existing methods for distributing tasks that need to be performed in near real time. The following scientific results were obtained as a result of the study: the method of clustering the fog environment supporting the Internet of Things was further developed by using a mathematical model of the initial distribution of the integrated cluster of computing resources, which improved the quality of grouping tasks and resources and contributed to the performance of the fog platform; for the first time, a model of elementary task flows of the Internet of Things using a fog platform was developed, which takes into account the features of distributed computing and allows decomposition of a coherent continuous sequence of input data; an improved set of methods for allocating resources of the fog environment supporting the Internet of Things, which differs from the known ones by the joint use of the developed model of elementary task flows and the clustering method, which made it possible to speed up the process of adaptive redistribution of resources and carry it out without suspending the transaction processing in cases of variable load and increased resource requirements, as well as significantly reduce processing time and balance the use of cloud resources when large data flows are received; the method of fast two-factor authentication between IoT devices was further developed by integrating the second factor into the authentication service with a centralized user database, which significantly reduced the time required to verify access authorization and ensure data confidentiality. The practical significance of the results is as follows: – increase the performance of the fog IoT platform by up to 9%. One of the key benefits is improved system performance due to optimized task distribution. This allows for faster and more efficient processing of data coming from IoT sensors and performing data processing tasks;– reduction of response time by up to 10%: the developed methods allow for more rational use of resources, such as computing power and network bandwidth. This leads to a reduction in the average response time of the system; – improving the method of fast two-factor authentication in foggy IoT environments. As a result of these improvements, the authentication speed has increased by 2.65 times when using this method for the considered fog platform; – development of modern applications: the results obtained make more scenarios for using IoT systems on the fog platform available. This expands the possibilities for applications in industries such as city management, industry, healthcare, and many others; – ensuring resilience and reliability by up to 3% on average: optimized methods make IoT systems more resilient to challenges and ensure reliable operation under load and change. Based on the study results, the practical and theoretical value of the developed methods was confirmed, practical recommendations were given on applying the developed methods, and prospects for their further development were considered.