Adapting Smart Waste Collection Systems through Operational Learning

Abstract

In this work, we consider a smart waste collection system where sensor-equipped bins can transmit information about their fill levels. Decisions about which bins to equip with sensors are typically made at a higher level, placing sensors at locations where they are expected to provide the greatest value. However, waste generation patterns may change over time, potentially reducing the effectiveness of these decisions. We discuss how operational data can be used within a learning framework to detect structural shifts in waste deposition patterns that significantly affect system performance and may indicate the need to revisit higher level decisions.

Bio: Dilay Aktas Dejaegere is a postdoctoral researcher at the KU Leuven Institute for Mobility (Belgium), where she also obtained her PhD. She has a background in operations research, and she studied the design and optimization of demand-responsive public bus systems during her PhD. She now works on optimization frameworks for smart waste collection systems.