Current projects
- Next generation enterprise-wide simulation and forecasting platform for Defence training and career continuums (@ATHENA Pro)
- AI-enabled lightweight simulator for Defence workforce planning (@ATHENA Lite)
- Automated scheduler and capacity analysis tool for ADF training systems/schools (@ARES)
- Data analytics toolbox (@IRIS)
- Training events scheduling and resource allocation for Seahawk Romeo training schoolhouse
- Optimisation of Recruitment to achieve capability
- Learning the landscape
Next generation enterprise-wise simulation and forecasting platform for Defence training and career continuums (@ATHENA Pro)
Defence career continuums are complex in nature. Personnel movements along these continuums are affected by internal policies and constraints, such as the availability of resources, the requirement for a specific proficiency or completion of a minimum time-in-level, as well as the level of demand for specific skills at specific ranks.
To model such transient system behaviour, while preserving common simulation architecture requires an easily reconfigurable simulation framework capable of explicitly representing the changing infrastructure, domain policies, constraints and flows. Flexibility is required to build and modify models and provide a repository of relevant data, as well as a database of historical changes.
The Workforce Analysis team designed a new approach that combines human intelligence and technology to extract more from human talent, employing state of the art Operations Research techniques that provide guaranteed best solutions - not just any solution that works. That is, stable and robust solutions (avoiding shortage or surplus of personnel numbers), providing significant cost savings. Furthermore, the team has employed high-end cognitive visualisation techniques, thus empowering decision makers to make the right decisions at the right time. The result is an enterprise-wide decision support system, ATHENA Pro that features:
- Representation of personnel flows along career continuums, including keys system performance indicators and intuitive diagnostics, such as bottlenecks, underflows, excessive queuing and more;
- Prediction or forecasting using hybrid discrete event and agent based simulation, novel use of active and passive probing for monitoring or goal setting;
- Strategic what-if scenario analysis, using design space exploration with depth-then-breath strategy;
- Visualisation of system health indicator to assist users at broad spectrum of ranks and positions to gain bird’s-eye view of capability health status and risk projections, as well as accurate statistics and measures of performance;
- An enterprise-wide persistent database that stores all information required to model and simulate career continuums, currently not available anywhere within Defence enterprise systems.
ATHENA Pro is delivered to the ADF on Defence network and is continuously improved to cater for a growing range of workforce planning question.
AI-enabled lightweight simulator for Defence workforce planning (@ATHENA Lite)
While ATHENA Pro provides an enterprise-wide solution for high-fidelity analysis of any Defence career pipelines, taking into account specific training and promotion policies and constraints, as well as for conducting a wide range of what-if analysis, there is a need for a lightweight simulator for performing quick analysis of personnel supply against demand. ATHENA Lite, a discrete event simulator, has been designed and developed specifically to perform computationally fast and less data intensive simulations. This is to enable the ultimate aim of integrating more advanced data analytics and machine learning techniques to further equip workforce analysts with an additional layer of artificial intelligence to explore all the intricacies inherent, but otherwise not obvious, in Defence workforce.
ATHENA Lite is on Defence network. The system is being continuously enhanced to handle additional modelling requirements.
Automated Scheduler and Capacity Analysis for ADF training systems/schools (@ARES)
ADF training establishments typically employ a number of staff to plan, schedule and manage the day-to-day operations of a school or squadron and produce daily or weekly schedules for staff, students, instructors, and other physical resources to meet the school’s training throughput and objectives.
The Workforce Analysis team is developing ARES, bespoke scheduling and planning tools, to automate much of the process. Moreover, this work aims to provide an answer on sufficiency of physical and human resources, in a training school, in order to achieve the target annual graduation numbers. A high fidelity simulation was developed to virtually replicate the operations of a training school, capturing on a minute-by-minute basis the movements of all students (pass/fail/repeat), as they are progressing through their training competencies and competing for the available resources, whilst respecting the school’s business rules.
The team delivered ARES for RAN’s Seahawk Romeo training squadron (725 SQN) and is working on ARES for DFSS and ALTC
Data analytics for workforce problems (@IRIS)
The Workforce Analysis team has been using various data analytics techniques for the analysis of Defence workforce simulations. IRIS extends this capability to create an analytical process in ATHENA to automatically sample a problem space and analyse the results. This will allow ATHENA users to explore the health of a particular workforce, provide insight into the sensitivity of various parameters and outputs, and examine the nth order interdependencies and effects of various inputs on outputs, as well as outputs on other outputs. These techniques will reduce the time-consuming, manual nature of sampling and analysis done currently.
Training events scheduling and resource allocation optimisation for Seahawk Romeo training schoolhouse
725 Squadron has replaced a number of staff in the planning cell with the ARES tool to automatically generate daily and weekly training program for the squadron. Our team is aiming to not just automate the scheduling process, but to also optimise the scheduling and planning solution.
The team is currently investigating a number of strategies for producing weekly plans/timetables, given students, syllabi, physical resources and instructors, with business rules acting as constraints. The first version of the Mixed Integer Linear Programming algorithm has been developed and tested, and soon to be delivered for operational use. Heuristic approaches are also being considered.
1. Esmaeilbeigi, R., Mak-Hau, V., Yearwood, J. and Nguyen, V. (2021), “The multiphase course timetabling problem”, European Journal of Operations Research (under review).
2. P. Lalbakhsh, V. Mak-Hau, R. Seguin, V. Nguyen, A. Novak, Capacity Analysis for Aircrew Training Schools – Estimating Optimal Manpower Flows Under Time Varying Policy and Resource Constraints, Proceedings of WinterSim 2018, Gothenburg, December 2018
Optimisation of recruitment, training and promotion to achieve capability
The career continuums from recruitment agencies through a complex course and posting structure to production of highly trained personnel is driven by operational needs of operational units. The effective determination of workforce recruitment and promotion targets is critical to delivering ADF capability. In this project, our team is working on developing an optimisation model, methodology and toolset, integrated into ATHENA Pro, to be used by Defence workforce planners to optimise recruitment, training and promotions in their services and workforces.
Previous work includes a representation of the structure as Markov Decision Process, solved using Dynamic Programming to derive a long term optimisation policy to gain significant savings.
The anticipated outcomes of this work include effective recruitment and promotion strategy, and efficient course scheduling and training plan.
1. S. Pike, B. Moran, D. Kirszenblat, A. Novak, A Stochastic Programming Approach to Optimal Recruitment in Australian Naval Aviation Training - “The Delta Model”, Proceedings of WinterSim 2018, Gothenburg, December 2018
2. B. Hill, D. Kirszenblat, B. Moran, A. Novak, Optimising Recruitment to Achieve Operational Capability Conditional on Appetite for Risk, Proceedings of WinterSim 2018, Gothenburg, December 2018
3. S. Suvorova, A. Novak, B. Moran, T. Caelli, Optimal recruitment strategies for Australian Naval Aviation training using Linear Programming and Dynamic Programming solutions - ''The price of thinking short term", Journal of Military Operations Research (2017), MOR1711 (accepted)
Learning the landscape
Optimisation methods are at the core of much of the work of the Workforce Analysis Team. Fundamental studies in a range of optimisation methodologies are in process to enhance and extend our use-driven research and development. One study is considering new methods for learning and modelling the fitness landscape based on Bayesian ideas. Related issues such as the need to understand how various constraints contribute to the convergence of optimisation algorithms are also being explored.