Integration of Social Behavioral Modeling for Smart Environments to Improve the Energy Efficiency of Smart Cities

Integration of Social Behavioral Modeling for Smart Environments To Improve Energy Efficiency of Smart Cities PI: Simone Silvestri(1), Co-PIs: Denise A. Baker(1), and Jhi-Young Joo(2) (1) Missouri University of Science and Technology (Missouri S&T) (2) Lawrence Berkeley National Laboratory Smart energy management is at the core of future smart cities, since energy profoundly impacts the city’s livablity, workability and sustainability. Key building blocks for smart energy management are intelligent residential environments, generally termed smart homes. These homes will include a plethora of smart interconnected appliances, realized through the Internet of Things paradigm, which can improve residential energy efficiency by monitoring and controlling the energy usage. Current approaches for automatic energy management systems have primarily focused on the observation and pattern recognition of past user activity without understanding the social and behavioral factors that influence these patterns (or lack thereof). In addition, current research in the field has failed to examine the psychological factors that impact user acceptance of such systems. However, enabling automatic energy management implicitly requires a loss of control for the user, which should not be neglected. Indeed, there are a number of psychological phenomena that may cause users to engage in wasteful energy consumption and/or to develop negative attitudes that can ultimately lead to abandonment and avoidance of such smart systems. This proposal aims at filling this gap by understanding and modeling the social and behavioral underpinnings involved in the human interaction with both smart appliances and smart energy management systems. These models will serve as the basis of a comprehensive framework for energy management of smart homes, which specifically addresses the psychological dimension of user behavior. The proposal addresses the CPS target areas Smart & Connected Communities (S&CC) and Science of Cyber-Physical Systems, by proposing new models and design principles that unify engineering and social behavioral perspectives of energy management in dynamic residential and community environments. This Synergy proposal addresses several challenges at the intersection of multiple disciplines. For this reason our team includes interdisciplinary researchers with complementary expertise in sensor networks and cyber-physical systems, social and behavioral sciences, and power/energy engineering. Intellectual Merit: The proposed research has the potential to transform the way in which energy management systems are studied and designed within the fields of computer science and electrical engineering by defining and integrating previously unexamined social behavioral models of user activities. Based on these models, we make use of graph theory to design formal user models that enable algorithm design and optimization. In addition, we propose machine learning techniques to correlate social behavioral dimensions to quantitative metrics observable by smart devices as well as algorithms that use this correlation to refine the user model. The formal models are used to design social-behavioral aware efficient algorithms for energy optimization for individual smart homes, as well as for communities of multiple homes in a microgrid. Our findings and approach will extend to other cyber-physical-human systems for which understanding social behavioral factors is critical in designing a socially responsive system. Further, our proposal examines key psychological factors related to autonomy that facilitate or hinder user engagement with energy management systems. Findings from these aspects of our proposal will extend and refine our knowledge on the societal implications of cyber-physical systems that seek to shift technological decision making from a human user to a technological control system. Broader Impacts: The proposed research integrates social behavioral aspects that affect the user perception and acceptance of smart environments with optimization and algorithmic tools for energy management. The results of this proposal will provide fundamental knowledge on how to design energy management systems of smart cities considering the social behavioral consequences of engineering design, therefore expediting the success of smart technologies and improving their impact on the city’s livablity, workability and sustainability. The team will create a comprehensive plan for wide-scale dissemination and adoption of the developed techniques and tools. The PIs will integrate the novel research findings into various courses within their departments, and develop courses listed across the departments. A number of students including females and minorities will develop interdisciplinary knowledge and skills in wireless networks, embedded systems, social sciences, and microgrid operation.