Project Description

Waste management has become an important issue and a growing global concern, as urban populations continue to increase and consumption patterns change. During 2015, 477 kg of municipal waste were generated per capita in Europe. This represents tonnes of waste that need to be collected and, to do so, thousands of kilometres are to be travelled with consequent thousands of Greenhouse Gases emissions. Nonetheless, there is high uncertainty regarding the amount of waste inside the bins that often leads to an inefficient collection operation where several kilometres are travelled to collect small amounts of waste.

A preliminary study conducted in Portugal reveals that only 40% of the recyclable waste bins collected by a waste collection company presented a fill level higher than 75%. This represents a high inefficient usage of the company’s resources and, unfortunately, is a common situation in the waste management systems. Thus, to increase resource efficiency, uncertainty regarding demand (e.g. the amount of waste that each bin contains) must be reduced or preferably eliminated. The access to real time bin’s fill levels through monitoring systems appears to be a solution. The recent advances in Information and Communication Technologies (ICT) makes possible to provide real time data through the use of sensors located inside the bins. However, the access to this data is not enough to increase the efficiency in the waste collection operation, making imperative to optimize collection routes accordingly. A tool to define optimal routes in a dynamic way given the information sent by the monitoring technology should be then pursued.

Some companies have been already exploring the use of waste container sensors coupled with tools to define routes, fact that reveals the relevance and importance of this problem. However, appropriate scientific methods to optimize routes given the information provided by the sensors are seldom studied in the literature and thus the existing solutions are still far away from optimized solutions that will be able to account for several important aspects that should be considered when planning the operation of such systems. For instance, knowing the waste amount at each bin does not necessarily mean that only full containers should be collected, on a specific day, as maybe considering small additional distances may reveal more profitable situations (e.g. collect not full containers located nearby a full container); the service level provided to the population must be considered; and defining the more “profitable” route for a day does not mean maximizing profit for a time horizon (as a decision of today often may have repercussions on the following days). Thus, an integrated optimized solution is required where these are just some issues that need to be studied and that have not yet been tackle in the existent solutions.

In this context, the present project proposes an innovative tool for smart waste management aiming to improve the quality of the operational decisions in the waste collection business. To achieve such goal, the aim of this research project is to:

• Given the volumetric sensors in use by one of the project’s partners, validate the accuracy of the data measured and define the requirements, in terms of information, needed for the real-time route planning tool;
• Develop and test a planning tool based on new mathematical models and state-of-the-art solution methods to define dynamic optimal routes considering the data provided by the sensors and accounting for the issues above mentioned;
• Assess the benefits of the real-time route planning tool and develop a cost-benefit analysis comparing the as-is to the to-be situation in a real case study.

Summarizing, the WSmart Route project aims to explore a new paradigm that relies on smart waste management, where real time data plays a central role in changing the way operations are managed today, moving from a static to dynamic routes definition. The tool to be developed will integrate technology with management concerns contributing to improve the companies’ operations decision-making process. Based on the team experience in static waste collection optimization and on preliminary results obtained from seminal studies on dynamic waste collection, it is estimated that the usage of a planning tool as the one proposed should lower companies’ operational costs around 35% and increase their kg/km ratio by 40%.

To accomplish the project’s goals a multidisciplinary team was assembled including members from two Portuguese Universities (ISTUL and UC), from the MIT, an industrial partner from the IT field (EVOX) and a recyclable waste collection company (ERSUC). The participation of the companies will enhance the innovative characteristics of the project, as it will enable the development of transferable solutions promoting the project economic value while expanding academic knowledge.

Research Team

CITTA

• António Pais Antunes

CEG-IST

• Tânia Ramos (coordinator)
• Ana Paula Póvoa
• 2 Grant-holders with a MSc (to hire).

Financial Support

• FCT (MIT-Portugal Program) - MITEXPL/SUS/0132/2017

Stage of Progress

• Concluded