IHS: An Intelligent Hybrid System for Conflict Resolution of IoT Services

Internet of Things (IoT) has become a common paradigm for various domains. More and more smart services are connected to the Internet by means of diverse intelligent edge devices. While people enjoy these convenient services, IoT service system will produce mass IoT data, which can be analyzed to improve service quality. In addition, these services usually coexist, which may lead to conflicts. Moreover, each user may have different kinds of needs. Suppose that in a smart home there are more than one person, a conflict may occur when they request the same service. We propose an intelligent hybrid system (IHS) to resolve IoT service conflicts, which consists of two steps, i.e., calculating historical preference mean and averaging on-site demand preferences. The first step is achieved by a weighted voting game (WVG) model, where machine learning is used to process historical IoT data and learn associated parameters. The second step is based on analytic hierarchy process (AHP) method, where some residents’ contextual factors are considered. Based on the system, we have launched a series of experiments. Experiment results based on real data sets demonstrate the efficacy of the proposed method in term of key accuracy metric, thereby validating our theoretical motivations and benefits.