As a major consumer of energy, the industrial sector must assume the responsibility for improving energy efficiency and reducing carbon emissions. However, most existing studies on industrial energy management are suffering from modeling complex industrial processes. To address this issue, a model-free demand response (DR) scheme for industrial facilities was developed. In practical terms, we first formulated the Markov decision process (MDP) for industrial DR, which presents the composition of the state, action, and reward function in detail. Then, we designed an actor-critic-based deep reinforcement learning algorithm to determine the optimal energy management policy, where both the actor (Policy) and the critic (Value function) are implemented by the deep neural network. We then confirmed the validity of our scheme by applying it to a real-world industry. Our algorithm identified an optimal energy consumption schedule, reducing energy costs without compromising production.INDEX TERMS Artificial intelligence, deep reinforcement learning, demand response (DR), industrial facilities, actor-critic.
I. INTRODUCTION A. BACKGROUND AND MOTIVATION
Industrial design (ID) undergraduate education in China is seen as a new rapidly growing discipline over the past 40 years. China's ID education is not well known in the West due to several barriers: language, the Great Firewall of China which blocks out most of the Western websites and a 12-h time difference. All Chinese ID curriculum and program information are available in Mandarin. The Ministry of Education administers all Chinese design education as well as ID scholarships and faculty exchange grants and its website and documents require translation. The Great Firewall of China blocks 90% of Western websites including Google making it difficult for Western Scholars to access accurate information about the size and shape of the Chinese ID education landscape. China has a historical relationship between the ID schools in China and the United States. Chinese students are studying or alumni of every American ID program. China and USA share similar program types, dual-track admissions for art and design streams, and academic calendars. In this paper, a model was developed to clarify the features of ID undergraduate education in China and USA, and a survey of eight ID schools was processed. Four aspects were comparatively discussed: (1) types of ID education, (2) ranking, evaluation, and certification of ID schools and programs, (3) curriculum, credits, course features, and yearly schedules of schools, (4) influences coming from the culture and globalization process. Based on the analysis, the similarities and differences in ID undergraduate education between the two countries are discussed. Results show the dual-track modes in China and USA are different. It is mainly reflected in the management and enrollment, curriculum organization, and cultural environment. Implications for the localization, openness, and globalization to ID education are finally discussed together with several directions for future development. The findings are valuable to USA and Chinese ID departments and faculty, researchers, staff and visiting scholars. It is also useful for university administrative units such as registrars, admissions, international offices and exchanges to understand each other.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.