Machine Learning Approach for Graphical Model-Based Analysis of Energy-Aware Growth Control in Plant Factories

Abstract

In recent decades, there has been a gradual penetration of plant factories achieving semiautomated crop cultivation. However, efficient energy utilization, as well as quality control of crops, are very important factors with regard to sustainable operation. Operating parameters, such as room temperature, affect not only the quality of crops but also the electric power required to realize the target operation while being influenced by the environment outside the plant. Therefore, a methodology is needed to analyze and interpret the relationships among these manipulated variables, exogenous variables, crop quality, and the amount of required electric power. Constructing a directed acyclic graph composed of regression models is an attractive approach for such analysis; however, the relationships can possibly be nonlinear, so the direct application of existing analytic approaches will not be appropriate. In this paper, we propose a methodology for relationship analysis among variables based on the directed acyclic graphs while identifying the linearity/nonlinearity in their relationships. In general, the construction of such a graphical model has computational issues, especially when the number of variables is large, and the risk of overfitting. The proposed method utilizes the idea of sparse regularization, which has been actively discussed in the field of machine learning, for realizing the automatic identification of linearity/nonlinearity between variables and screening redundant candidate structures; this approach relaxes the computational complexity issue and controls the risk of overfitting. As a case study, the proposed method is applied to a dataset collected from a real-world cultivation system in a plant factory to discuss its usefulness. INDEX TERMS Analysis of plant data, directed graphical model, energy-aware plant growth control, identification of linearity/nonlinearity, overlap group lasso, plant factory, sparse partially linear model.

RETRACTED ARTICLE: Prescriptive analytics applications in sustainable operations research: conceptual framework and future research challenges

“…There are 15 papers (37.5%) in this subset. With the shift towards the digital era, the role of Machine Learning in attaining sustainability is deemed to receive much attention (Breiman, 2001 ; Ceballos-Fuentealba et al, 2019 ; Chahidi et al, 2021 ; Chu et al, 2019 ; Diaz et al, 2021 ; Duan et al, 2020 ; Fallah et al, 2018 ; Fujimoto et al, 2019 ; Hegedűs et al, 2021 ; Lim et al, 2017 ; Rafique & Jianhua, 2018 ; Schreiber et al, 2021 ; Shaharum et al, 2020 ; Trivedi et al, 2021 ; Tsai et al, 2011 ).…”

“…ML based approach has also been used to assess the crop quality and consumption of electricity (Fujimoto et al, 2019 ), to forecast energy load in smart energy management grids (Fallah et al, 2018 ), to address the sustainable operations of power control by incorporating energy harvesting and internet of things (Chu et al, 2019 ), to reduce waste and conserve industrial resources and implement process graph framework to deal with resource conservation network issues (Lim et al, 2017 ), to evaluate the relationship between sustainable operation of rail transit and land use by employing data envelopment analysis (Duan et al, 2020 ) and to achieve sustainable transportation, explore vehicle automation through closed loop matching where the dataset is generated, trained and evaluated using neural network (Hegedűs et al, 2021 ).…”

Plant Factory: A New Playground of Industrial Communication and Computing

“…The authors in [ 11 , 12 ] have a quantified and qualified evaluation of energy demand and carbon footprint of vertical farming, emphasizing its significance to city sustainability and climate change. Although the technology development for vertical farming is much more radical than the industry within a single discipline, such as LED lighting [ 13 ], software control system [ 14 ], machine learning [ 15 ] and big data [ 16 ], these single-disciplinary innovations are far from an integrated and systematic solution that is demanded by the industry.…”

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

“…These basic technologies have contributed to the foundation of advanced energy management systems in the current distribution networks [36][37][38][39]. The penetration of distributed power sources and controllable energy appliances and market liberalization have spread the concept of energy management to the demand side, that is, households [40][41][42][43][44][45][46][47][48][49], office buildings [47,[50][51][52][53][54], factories [55][56][57][58][59][60][61] and even to districts [62][63][64][65][66][67]. From historical viewpoints, the development of technology for local EMSs and the concern about interaction among different systems motivated the recent activities in the field related to cooperated EMSs; the concept of system-of-systems [68,69] has also emphasized research related to cooperated EMSs as a concrete application field.…”