Machine-Learning Methods to Select Potential Depot Locations for the Supply Chain of Biomass Co-Firing

Abstract

Coal is the second-largest source for electricity generation in the United States. However, the burning of coal produces dangerous gas emissions, such as carbon dioxide and Green House Gas (GHG) emissions. One alternative to decrease these emissions is biomass co-firing. To establish biomass as a viable option, the optimization of the biomass supply chain (BSC) is essential. Although most of the research conducted has focused on optimization models, the purpose of this paper is to incorporate machine-learning (ML) algorithms into a stochastic Mixed-Integer Linear Programming (MILP) model to select potential storage depot locations and improve the solution in two ways: by decreasing the total cost of the BSC and the computational burden. We consider the level of moisture and level of ash in the biomass from each parcel location, the average expected biomass yield, and the distance from each parcel to the closest power plant. The training labels (whether a potential depot location is beneficial or not) are obtained through the stochastic MILP model. Multiple ML algorithms are applied to a case study in the northeast area of the United States: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and Multi-Layer Perceptron (MLP) Neural Network. After applying the hybrid methodology combining ML and optimization, it is found that the MLP outperforms the other algorithms in terms of selecting potential depots that decrease the total cost of the BSC and the computational burden of the stochastic MILP model. The LR and the DT also perform well in terms of decreasing total cost.

A supervised machine-learning method for optimizing the automatic transmission system of wind turbines

“…Jiang et al (2019) used logistic regression for predictions of aflatoxin in grain at a postharvest stage, providing a base for guaranteeing the safety of stored grain by providing early warning on contaminant problems emerging while storing the product. Goettsch et al (2020) used a multi-layer perceptron algorithm in a mathematical modeling problem where the aim was to decrease gas emissions by optimizing the biomass supply chain. There are novel research studies for using supervised machine learning methods in production planning.…”

Green supply chain transformation and emission reduction based on machine learning

“… 35 , 36 Based on various ML algorithms, most studies focus on supplier selection, 37 – 39 whereas others focus on supply chain risk management. 40 Moreover, few authors have focused on inventory management, 41 and few authors center on demand forecasting. 42 These studies fully revealed the positive significance of ML in SCM.…”

Machine Learning-Based Problem Space Reduction in Stochastic Programming Models: An Application in Biofuel Supply Chain Network Design

“…Based on these challenges, machine learning has gained traction as a tool to reduce the computational burden of complex optimization models [5], [6]. Goettsch et al utilized machine learning to reduce the number of potential depot locations for biomass cofiring [7].…”