PhD Defence: Machine Learning Algorithms for Smart Electricity Markets


In his dissertation ‘Machine Learning Algorithms for Smart Electricity Markets’ ERIM’s Markus Peters confronts the decentralization of energy production in the face of renewable sources, electric mobility, and related advances, which are usurping traditional, centralized power systems based on inelastic demand. Markus demonstrates that such issues can be alleviated through use of Smart Markets and Information Systems to engender forms of cooperation which leverage real-time consumption and price data to incentivize efficiency within operational constraints. Guidance on the design of Information Systems for sustainable electricity systems is prescribed, with a discussion of their potential societal positives and negatives.

Markus defended his dissertation in the Senate Hall at Erasmus University Rotterdam on Thursday, the 13th of February 2015. His supervisor was Professor Wolfgang Ketter. Other members of the Doctoral Committee included Professor Eric van Heck (ERIM), Professor Tom Heskes (Radboud University Nijmegen), and Professor Maytal Saar-Tsechansky (McCombs School of Business).

About Markus Peters

Markus Peters was born on July 12, 1978 in Neuss, Germany. From 1999 to 2005 he studied Computer Science (Data Mining) and Business Administration (Operations Research) at the University of Aachen. Supported by a Fulbright fellowship, he spent the 2003/2004 academic year at Rensselaer Polytechnic Institute in Troy, NY where he obtained a Master’s degree in Information Technology.

After his graduation, Markus worked as IT consultant, first for Deloitte’s Business Intelligence (BI) service line and later independently. He advised clients in manufacturing, logistics, marketing, and software development on the design and implementation of enterprise BI systems, and on software engineering topics more generally.

Markus entered the graduate program at the Erasmus Research Institute of Management (ERIM) in 2011 to work on Machine Learning algorithms for future retail electricity markets. For this work, he was awarded with the ERIM Master’s degree in Business Research in 2012.

Markus’ work has appeared in Data and Knowledge Engineering and in the Machine Learning Journal, and it has been presented at various conferences such as the Conference of the Association for the Advancement of Artificial Intelligence (AAAI), the Conference on Information Systems and Technology (CIST), the European Conference on Machine Learning (ECML), and the Workshop on Information Technology and Systems (WITS).

Thesis Abstract

The shift towards sustainable electricity systems is one of the grand challenges of the twenty-first century. Decentralized production from renewable sources, electric mobility, and related advances are at odds with traditional power systems where central large-scale generation of electricity follows inelastic consumer demand. Smart Markets and intelligent Information Systems (IS) could alleviate these issues by providing new forms of coordination that leverage real-time consumption information and prices to incentivize behaviors that remain within the grid's operational bounds. However, the best design for these artifacts, and the societal implications of different design choices is largely unclear. This dissertation makes three contributions to the debate. First, we propose and study a design for Brokers, a novel type of IS for autonomous intermediation in retail electricity markets. Second, we propose a probabilistic model for representing customer preferences within intelligent IS, and we study its performance in electricity tariff and other choice tasks. And third, we propose and study Competitive Benchmarking, a novel research method for effective IS artifact design in complex environments like Smart Grids where the social cost of failure is prohibitive. Our results provide guidance on IS design choices for sustainable electricity systems, and they highlight their potential societal positives and negatives.