Optimal Mobility and Communication Strategy to Maximize the Value of Information in IoT Networks

Internet of Things (IoT) is an emerging next-generation technology in the fourth industrial revolution. The Industrial IoT is required to transmit the collected data in a timely manner to support real-time monitoring, control and automation. In such systems, the timeliness of information is very important, and meanwhile, different physical processes have different requirements on the accuracy of timeliness. However, existing performance metrics, such as the Age of Information (AoI), are unable to fully evaluate the timeliness of information with heterogeneous physical processes. Recently, we proposed an information-theoretic metric named the “Value of Information” (VoI) to measure the usefulness of information in the context of a heterogeneous and noisy environment. In this work, we study a joint path planning of the mobile robot and user scheduling optimization problem in Industrial IoT networks with the aim of maximizing the minimum VoI among all users under mobility and communication constraints. We formulate this optimization problem as a Markov decision process, and propose a reinforcement learning-based algorithm to find the VoI-aware mobility and communication strategy efficiently. Through numerical results, we show that the proposed method can capture the impact of data freshness, inherent correlation characteristics of underlying data sources and noise on the usefulness of information. Compared with the existing AoI-aware strategy, the proposed VoI-aware strategy achieves better performance by exploiting the heterogeneity of data sources especially when the wireless resource is limited.