Assessing the Impact of Edge Computing on IoT Device Performance in Smart Homes

Thesis Abstract

The rapid proliferation of Internet of Things (IoT) devices within smart home environments has increased the demand for efficient and reliable data processing architectures to support seamless device interoperability, security, and user experience. Traditionally, IoT devices rely heavily on cloud-based infrastructures for data processing and decision-making, which often results in increased latency, bandwidth consumption, and concerns regarding data privacy. The advent of edge computing offers a promising alternative by decentralizing data processing closer to the source, potentially enhancing device performance, response times, and system resilience. However, comprehensive empirical assessments of how edge computing impacts IoT device performance within smart homes remain limited, necessitating systematic investigation to inform future deployment strategies. The primary aim of this study is to evaluate the effects of edge computing integration on the performance metrics of IoT devices operable in smart home contexts. Specific objectives include (1) examining the latency reductions achieved through edge computing, (2) assessing improvements in energy efficiency of IoT devices, (3) analyzing system reliability and fault tolerance, and (4) identifying user perceptions towards performance enhancements influenced by edge architectures. To fulfill these objectives, the study adopts a mixed-method empirical approach combining quantitative performance measurements with qualitative user surveys. The research utilizes a quasi-experimental design involving two groups of operational smart homes one employing traditional cloud-dependent IoT architectures and the other integrated with localized edge computing nodes. A total of 60 smart homes, evenly split between the two conditions, are selected through purposive sampling—30 homes per group—ensuring variation in household size, device types, and geographical locations to enhance generalizability. Data collection instruments include network performance analyzers to measure latency and bandwidth utilization, energy consumption meters to assess device efficiency, and structured questionnaires and interview guides to capture user perceptions and system reliability feedback. Data analysis encompasses quantitative techniques such as multiple regression analysis and ANOVA to determine the statistical significance of differences in performance metrics, with attention to confounding variables like device age and household activity levels. Thematic analysis is applied to qualitative responses to glean insights into user experiences and satisfaction levels, while a theoretical framework grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT) and the Performance Optimization Model provides a conceptual basis for interpreting findings. Expected findings suggest that edge computing significantly reduces latency by an average of 45%, enhances energy consumption efficiency by approximately 22%, and improves overall system reliability by decreasing failure rates associated with network congestion. Additionally, user perceptions indicate increased satisfaction with responsiveness and perceived security in edge-enabled environments. These results are anticipated to demonstrate that deploying edge computing architectures substantively bolsters IoT device performance in smart homes, thereby advancing the operational efficiency and user acceptance of such systems. This study contributes to the existing body of knowledge by providing empirical evidence quantifying the benefits of edge computing in residential IoT systems, offering practical insights for industry stakeholders regarding optimal deployment strategies, and informing policymakers on infrastructure investment priorities. The findings underscore the importance of strategic edge integration to address current limitations associated with cloud-dependent IoT ecosystems. Concluding, the research recommends broader adoption of edge computing frameworks within smart homes, emphasizes establishing standardized protocols for seamless integration, and highlights avenues for future longitudinal studies to investigate long-term operational impacts. Overall, the study advances understanding of the transformative potential of edge computing, fostering more resilient, efficient, and user-centric smart home IoT ecosystems.