Learning How to Communicate in the Internet of Things: Finite Resources and Heterogeneity

Abstract

For a seamless deployment of the Internet of Things (IoT), there is a need for self-organizing solutions to overcome key IoT challenges that include data processing, resource management, coexistence with existing wireless networks, and improved IoT-wide event detection. One of the most promising solutions to address these challenges is via the use of innovative learning frameworks that will enable the IoT devices to operate autonomously in a dynamic environment. However, developing learning mechanisms for the IoT requires coping with unique IoT properties in terms of resource constraints, heterogeneity, and strict quality-of-service requirements. In this paper, a number of emerging learning frameworks suitable for IoT applications are presented. In particular, the advantages, limitations, IoT applications, and key results pertaining to machine learning, sequential learning, and reinforcement learning are studied. For each type of learning, the computational complexity, required information, and learning performance are discussed. Then, to handle the heterogeneity of the IoT, a new framework based on the powerful tools of cognitive hierarchy theory is introduced. This framework is shown to efficiently capture the different IoT device types and varying levels of available resources among the IoT devices. In particular, the different resource capabilities of IoT devices are mapped to different levels of rationality in cognitive hierarchy theory, thus enabling the IoT devices to use different learning frameworks depending on their available resources. Finally, key results on the use of cognitive hierarchy theory in the IoT are presented.key property of low-cost, low-capability MTDs is low computational capability as discussed in [1] and [18]. However, existing learning frameworks, such as decision trees [18] or reinforcement learning [13] and [28], can be

Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues

“…While in [14], the applications of machine learning in wireless sensor networks (WSNs) are discussed, and the advantages and disadvantages of each algorithm are evaluated with guidance provided for WSN designers. In [15], different learning techniques, which are suitable for Internet of Things (IoT), are presented, taking into account the unique characteristics of IoT, including resource constraints and strict quality-of-service requirements, and studies on learning for IoT are also reviewed in [16]. The applications of machine learning in cognitive radio (CR) environments are investigated in [17] and [18].…”

Machine Learning in IoT Security: Current Solutions and Future Challenges

“…RL techniques learn by exploiting various stages and develop the reward and action relationship between agent and the environment. This relationship of action reward is very useful in solving various IoT problems [101]. It does not require extensive training data set; however, the agent is required to have the knowledge of the state transition function.…”

A Directed Information Learning Framework for Event-Driven M2M Traffic Prediction

“…Naturally, once an event happens, some MTDs will initiate the access process before others. This is a practical assumption since most IoT events propagate through a geographical area, and sensors sense them at different times [12]. As discussed earlier, the BS will have information on a history of prior data traffic for event-driven MTCs.…”