CARD: Context-Aware Resource Discovery for mobile Internet of Things scenarios

Abstract

The occurrence of short but recurrent opportunistic contacts between static infrastructure and mobile devices largely characterizes recent Internet of Things (IoT) applications for Smart Cities and Smart Buildings scenarios. In order to efficiently exploit such existing communication opportunities to access services, share and collect data, IoT applications cannot rely on standard discovery mechanisms that periodically probe the environment to discover resources. Discovery protocols resilient to different contact opportunities and able to optimize energy consumption when device contacts are not present are therefore required in order to avoid waste of energy especially in battery operated user devices. Additionally, such new discovery protocols need to optimize the time available for communication operations, while being able to adjust to application requirements, and balance energy consumption with respect to latency for contacts discovery. To this aim, we introduce CARD, a Context Aware Resource Discovery framework that leveraging QLearning techniques extends the functionalities of asynchronous neighbor discovery protocols, while being capable to reduce energy wastage and discovery latency. Simulation results show that CARD performs better than existing approaches and is resilient to a variety of real scenarios characterizing Smart Cities and Smart Building deployments.

Internet of Things: A Scientometric Review

“…Education, Learning, E-Learning, and mobile learning is the fifth top application in this list, with 93 publications and the United Kingdom as the leading country with 12 documents. The most popular related topics with education are: augmented reality [141][142][143], context aware [144][145][146], and near field radio technologies such as RFID [147][148][149] and Near Field Communication (NFC) [150,151].…”

An Arrival and Departure Time Predictor for Scheduling Communication in Opportunistic IoT

“…Finally, the Context Aware Resource Discovery of Pozza et al [21] reports an algorithm which learns the optimal schedule in order to jointly optimize energy efficiency and discovery latency. This discovery approach exploits Q-Learning [39] to learn by trial-and-error the optimal sequence of discovery action, composed by low latency sub-actions and high latency sub-actions, which maximizes the long term reward driven by contact discoveries.…”

“…Similarly to CARD [21], the actions for LPS and HPS are, respectively high latency and low latency actions as such: High Latency Action (HLA) guaranteeing discovery within a temporal bound $t_{HLA}=D$. Low Latency Action (LLA) guaranteeing discovery within a temporal bound $t_{LLA}=0.05·D$. where the parameter D is decided by application requirements. As in CARD, the general temporal overlap driven approach by Dutta et al [43] was used, relying on prime numbers properties to guarantee overlap between asynchronous nodes.…”

“…Recent research has shown that is possible to either learn [19,20,21] about such encounters or probabilistically, through statistical analysis, [22,23] adapt neighbour discovery in order to improve lifetime of devices and optimize communication time. We argue that the learning process is necessary in order to adapt online to the statistics of the pattern of encounters, and is optimizable by identifying the significant features of statistics of mobility such as spatial or temporal recurrence or contextual knowledge.…”

“…We argue that the learning process is necessary in order to adapt online to the statistics of the pattern of encounters, and is optimizable by identifying the significant features of statistics of mobility such as spatial or temporal recurrence or contextual knowledge. While in the authors’ previous work CARD [21], neighbour discovery is adapted based on the acquired knowledge, in this work an algorithm for learning and predicting the actual values of “arrival” and “departure” of IoT devices is proposed.…”