Intelligent Job Scheduling: Better Service for Less Carbon

Manual job scheduling is a resource-consuming operation that routinely results in sub-optimal customer service, inefficiently utilised, dissatisfied workforce, and decision making that is slow to adapt to real-time developments; all at a high environmental cost. These symptoms have long been affecting the engineering service industry, with on-site maintenance providers frequently reporting operational losses due to the cumbersome logistics of dispatching engineers
to attend calls at client locations. Intelligent scheduling via evolutionary Artificial Intelligence offers a promising route towards finding effective solutions to this host of problems. We have leveraged this potential to build an innovative end-
to-end scheduling optimisation algorithm featuring customised components: (1) a tailored Evolutionary Algorithm equipped with a robust schedule encoding and decoding mechanism as well as bespoke genetic and fitness tuning operators; (2) a clustering heuristic that groups jobs according to their proximity to relevant engineers leading to an initial population of higher quality candidate solutions, (3) a computational efficiency booster performing calculations and caching of distance and duration matrices by means of parallel computing, and (4) a persistent solution storage and retrieval mechanism optimising real-time alternative timeslot proposal. These have been carefully configured, enhanced,
and combined to produce a robust software platform that evolves job schedules meeting realistic, dynamic operational restrictions. We demonstrate, based on evidence produced by running a comprehensive set of experiments, that our
algorithm efficiently improves the key performance indicators of a real-world on-site engineering services provider, Thames Laboratories. We are successfully automating the company’s customer attendance logistics, enabling better
decision-making support for the organisation’s leadership. This case study highlights the significance of our AI-powered algorithm’s impact on transforming the relevant industry for the better, in full alignment with environmental sustainability best practice, and provides a strong argument for larger scale distribution and adoption across commercial and public administration sectors alike.