Fangyi Xu’s research while affiliated with Jilin University of Finance and Economics and other places

Industry 4.0 has ushered in a new era of technological advancements, particularly in smart production, using technologies like the Internet of Things, big data analytics, and artificial intelligence. While much attention has been focused on the technological and economic aspects of this transformation, the concept of social sustainability within smart production remains underexplored. This paper explores the intersection of technology and social sustainability in the context of smart production in China. Machine learning, especially in hybrid models, is examined as a tool to integrate social sustainability into smart production. These algorithms can analyze vast datasets, predict social disruptions, inform policymaking, and tailor technological solutions. The paper presents a comprehensive analysis of the performance of various machine learning models in forecasting solar PV energy production, with a focus on different photovoltaic technologies and emission scenarios. The results highlight the robustness of certain photovoltaic technologies, such as p-Si and m-Si, in the face of climate variability. The study introduces the MLP-CARIMA-GPM model as a benchmark in predicting solar PV energy output, challenging the traditional belief that composite models always offer superior results. Theoretical and policy implications are discussed, emphasizing the importance of aligning solar PV energy production with Sustainable Development Goals. The research underscores the pivotal role of sophisticated, hybrid machine learning models in ensuring sustainable energy production and offers valuable insights for policymakers, industry leaders, and stakeholders navigating the challenges of energy demands, climate change, and technological advancements. This study serves as a roadmap for achieving sustainable smart production, where technology and sustainability coalesce to illuminate possibilities for the future.