Abstract

Renewable energy sources have been pursued as a means of mitigating carbon emission from the energy sector. As biomass resources are a part of natural carbon cycle, they have the potential to mitigate carbon emissions as a renewable source while reducing waste and residues. It shall be noted that biomass has its own challenges as well. Seasonality and disruption risks are some of the disadvantages of biomass resources. Therefore, it is imperative that biomass supply chains be managed such that to withstand disruptions and provide customers with reliable stocks available. In recent years, there has been a growing attention to research on energy supply chain resilience. In case of biomass, most studies have integrated predictions for either supply or demand side of biomass supply chains. This study aims at addressing this gap by formulating biomass supply chain resilience subject to integrating the predictions from both supply and demand dimensions. In doing so, we compare the performance of a host of machine learning techniques combined with routing algorithms. A case study with real (supply and demand) data is considered to present the applicability and usefulness of the proposed methodology accompanied by a results analysis. We then conclude by summarizing the contributions, limitations, and presenting opportunities for future research.