Research Repository

Many-Objective Genetic Type-2 Fuzzy Logic Based Workforce Optimisation Strategies for Large Scale Organisational Design

Starkey, Andrew J (2018) Many-Objective Genetic Type-2 Fuzzy Logic Based Workforce Optimisation Strategies for Large Scale Organisational Design. PhD thesis, University of Essex.


Download (5MB) | Preview


Workforce optimisation aims to maximise the productivity of a workforce and is a crucial practice for large organisations. The more effective these workforce optimisation strategies are, the better placed the organisation is to meet their objectives. Usually, the focus of workforce optimisation is scheduling, routing and planning. These strategies are particularly relevant to organisations with large mobile workforces, such as utility companies. There has been much research focused on these areas. One aspect of workforce optimisation that gets overlooked is organisational design. Organisational design aims to maximise the potential utilisation of all resources while minimising costs. If done correctly, other systems (scheduling, routing and planning) will be more effective. This thesis looks at organisational design, from geographical structures and team structures to skilling and resource management. A many-objective optimisation system to tackle large-scale optimisation problems will be presented. The system will employ interval type-2 fuzzy logic to handle the uncertainties with the real-world data, such as travel times and task completion times. The proposed system was developed with data from British Telecom (BT) and was deployed within the organisation. The techniques presented at the end of this thesis led to a very significant improvement over the standard NSGA-II algorithm by 31.07% with a P-Value of 1.86-10. The system has delivered an increase in productivity in BT of 0.5%, saving an estimated £1million a year, cut fuel consumption by 2.9%, resulting in an additional saving of over £200k a year. Due to less fuel consumption Carbon Dioxide (CO2) emissions have been reduced by 2,500 metric tonnes. Furthermore, a report by the United Kingdom’s (UK’s) Department of Transport found that for every billion vehicle miles travelled, there were 15,409 serious injuries or deaths. The system saved an estimated 7.7 million miles, equating to preventing more than 115 serious casualties and fatalities.

Item Type: Thesis (PhD)
Uncontrolled Keywords: workforce optimisation fuzzy logic organisational design many objective genetic algorithms optimization
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Andrew Starkey
Date Deposited: 02 Mar 2018 09:56
Last Modified: 02 Mar 2018 09:56

Actions (login required)

View Item View Item