Effective GA approach for municipal solid waste collection: dynamic capacitated vehicle routing in smart cities
by Abdelfetah Hentout; Abderraouf Maoudj; Ahmed Kouider; Mustapha Aouache
International Journal of Artificial Intelligence and Soft Computing (IJAISC), Vol. 7, No. 4, 2022

Abstract: Currently, municipal solid waste (MSW) collection is based on ineffective and inflexible static routing models done once a day by trucks. Given a set of fixed bins distributed over a specified area, trucks move along their predefined routes to collect the bins contents. It is also revealed that logistics costs for collection and recycling represent 95% of total cost; thus, minimising total travelled distances using minimum vehicles is of a key importance. This paper presents a genetic algorithm-based solution for municipal solid waste collection and monitoring at smart cities modelled as a capacitated vehicles routing problem (CVRP). This solution adopts two crossover techniques and three mutation methods applied on the population divided into three subsets. Experimental results over various benchmarks show the effectiveness and superiority of the proposed approach in terms of runtime and solution quality. Finally, a real case study of 50 sites (49 bins + a depot) and ten trucks is deployed in the City of Baba Hassen, Algiers, Algeria.

Online publication date: Thu, 27-Apr-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Artificial Intelligence and Soft Computing (IJAISC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com