Title: Application of big data copula-based clustering for hedging in renewable energy systems

Authors: Iddrisu Awudu; William W. Wilson; Mahdi Fathi; Khalid Bachkar; Bruce Dahl; Adolf Acquaye

Addresses: Department of Management, Quinnipiac University, USA ' Department of Agribusiness and Economics, North Dakota State University, USA ' Department of Information Technology and Decision Sciences, University of North Texas, Denton, USA ' Department of International Business and Logistics, California State University Maritime Academy, USA ' Deceased; formerly of: North Dakota State University, USA ' Department of Mechanical and Industrial Engineering, Rochester Institute of Technology-Dubai, Dubai, UAE

Abstract: In this paper, we formulate an optimisation-hedging model which demonstrates how operational research methods and analytics can take advantage of big data sources to inform business decisions in the renewable energy sector. This is achieved by incorporating an analytical technique called co-cluster (copula clustering) algorithm in measuring risks confronting a renewable energy producer. The model development and co-cluster methodology are illustrated using an empirical case study under three market scenarios for an ethanol producer. Our results show that adopting the co-cluster algorithm gives the ethanol processor an improved risk management strategy by capturing marginal relationships among the input and output prices; hence highlighting the advantages of big data and data analytics in business decision making within the renewable energy sector.

Keywords: big data; renewable energy; revenue; risk hedging.

DOI: 10.1504/IJRM.2020.110633

International Journal of Revenue Management, 2020 Vol.11 No.4, pp.237 - 263

Received: 06 Jan 2020
Accepted: 06 May 2020

Published online: 26 Oct 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article