Applying the Random Backoff Algorithm for Active Information Exchange Control in Smart Internet Environment Server

Abstract

The information exchange-as a way of interaction for participants in an Internet environment-is a fundamental function of a distributed system within the computing paradigms of Internet of Things, Cyber-Physical Systems, Ambient Intelligence etc. Participants in an Internet environment are represented by software agents running typically on low-performance edge computing devices. Interaction is implemented through exchange of information collected by the participants in a shared information store that implements the «intelligence» of this environment. The organization of agents access to the shared information and of their interaction uses a semantic information broker that manages information flows between participants. With an increase in the number, diversity, and activity of participants, the workload on the broker and the data transmission network increases. In this paper, a novel method is proposed to reduce the workload by delegating part of the control of the information exchange to the participants themselves. The subscription mechanism is modified for information changes in a shared information store. Instead of the passive op­tion, when the broker must notify all agents who have subscribed to the information being changed, the active option is used, when agents themselves can check for information changes. A new two-component control method based on the well-known backoff algorithm in combination with the well-known adaptive strategy for choosing the time of sending the next request from an agent to a broker for the presence of information changes is proposed. The control capabilities are studied experimentally using a simulated Internet environment.