Statistics

Workflow management system

Renewable energy

Workflow technology

Programming language

Efficient energy use

Database

Engineering

Artificial intelligence

Factory (object-oriented programming)

Energy (signal processing)

Mathematics

Workflow

Computer science

Electrical engineering

Energy Reports

Artificial intelligence (AI) controls are commonly used to save energy. However, excessive diversity in technological development has resulted in the inability to provide consistent energy-saving effects. Therefore, this study analysed 164 academic papers, with a total of 113 AI methods applied in six different fields of application. A universal workflow was developed to identify workable AI technologies for energy saving. The concept of a universal workflow originates from machine learning (ML). To approach an ML problem, a workflow is constructed to assist researchers in defining their problem and assembling a dataset. In this study, the developed universal workflow adopted a hierarchical structure to guide users to choose learning, optimisation, and control tools to achieve energy saving. Based on the data from various studies, the developed workflow provides qualitative and quantitative energy-saving effects for application in diverse fields. Universal workflow has contributed to the development of ML for commercial applications, and this research is also targeted to facilitate the commercial application of AI in the field of energy saving. Through a comprehensive analysis of experimental data, the universal workflow can confirm 35% energy cost saving in the building; 25% energy saving of the heating, ventilation and air conditioning equipment; 50% artificial lighting system energy saving; up to 70% reduction of information transfer and communication power; a continuous output of 30% peak power from the renewable energy device to the microgrid; and 20% power demand reduction in the factory. Corresponding to the choice of application technology, to the qualitative and quantitative benefits, and to the difference in control response, the universal workflow developed in this study provides a workable method to assist the use of AI in various applications. With workable design guidelines, the acceleration of commercial applications of AI for energy saving can be expected.

Universal workflow of artificial intelligence for energy saving