Real World Applications

Director: Dr Aneta Neumann

Evolutionary Mine Scheduling under Uncertainty

Long-term planning and production scheduling are among the most critical tasks in the area of mining. The goal is to extract valuable ore from an orebody in a sequence that takes into account many mining and precedence constraints in a way that is economically efficient. This is an important real-world optimisation problem that has been studied in the literature over many years. Evolutionary computation techniques have successfully been applied in the area of mining, in particular to large scale optimisation problems such as the cost efficient extraction of ore, the ore processing and blending problem, and the large-scale open pit mine scheduling problem. Uncertainty is a feature common to many financial investments. For example, when investing in shares there is uncertainty around the future performance of the stock. This creates considerable risk as well as the potential for big reward. Along the same lines, uncertainty around the true composition of mineral deposits comes with considerable financial risk when investing in a mining operation.

Advanced Mine Optimisation under Uncertainty

Evolutionary algorithms provide great flexibility in dealing with a wide range of optimisation problems. This includes highly constrained problems as well as problems involving stochastic components. Their wide applicability has made evolutionary computing techniques popular optimisation techniques in areas such as engineering, finance, and supply chain management. The area of mining where the goal is to extract ore in a cost efficient way poses large scale optimisation problems, and evolutionary computation techniques have successfully been applied in this area. We consider the problem of mine planning and focus on uncertainties which highly impact the mine planning process. Mine planning is one of the key optimisation problems in mining and a wide range of approaches have been developed over the years. The classical article of Lerchs and Grossmann introduced the basic problem formulation and provided a dynamic programming approach. Over the years, a wide range of mine planning approaches taking different characteristics of this important real-world optimisation problem into account have been studied in the literature. This includes integer programming approaches based on block scheduling and heuristic techniques that are able to deal with various characteristics such as uncertainties of the problem.

Evolutionary Time-Use Optimization for Improving Health Outcomes

A real-world multi-objective optimization problem is "How should children spend their time (i.e. sleeping, sedentary behaviour and physical activity) to optimize their health, well-being, and cognitive development?". The importance of this problem has led governing bodies and health authorities such as the World Health Organization (WHO) to provide guidelines for daily durations of sleep, screen time, and physical activity. Such guidelines for school-aged children (5-12 years) currently recommend 9-11 hours of sleep, no more than 2 hours of sedentary screen time, and at least 1 hour of moderate-to-vigorous physical activity (MVPA) per day. However, these guidelines are primarily underpinned by systematic reviews collating evidence of how the duration of a single behaviour, such as MVPA, is associated with a single measure of health or wellbeing. These studies show whether more or less of behaviour is beneficially associated with the outcome, rather than identifying optimal durations, which would be required to support recommendations for daily durations of the behaviour. Almost no studies have attempted to define optimal durations for these activity behaviours for a single health outcome, let alone for multiple health and well-being outcomes.

Diversity Optimization for Communication Networks

In recent years, computing diverse sets of high quality solutions for an optimization problem has become an important topic. The goal of computing diverse sets of high quality solutions is to provide a variety of options to decision makers, allowing them to choose the best solution for their particular problem. In recent years, the Low Probability of Detection (LPD) problem has gained significant attention in the mobile networks and data privacy/security community. LPD is concerned with the technological development that enables the successful detection and concealment of certain activities or objects in wireless systems and networks for all voice and data communication. The problem seeks to connect nodes in a network in a way that minimizes the amount of physical area occupied by the network. This makes it more difficult for an adversary to detect the network due to the reduced physical footprint. Solving the problem is useful in phone networks, wireless local area networks, satellite communication networks, and other security-sensitive industrial applications where maintaining a low profile is important. Evolutionary diversity optimization can be used to effectively provide diverse sets of high quality solutions for the concealment of communication networks in large settings.

Publications

• A. Neumann, S. Goulder, X. Yan, G. Sherman, B. Campbell, M. Guo, F. Neumann: (2023): Evolutionary Diversity Optimization for the Detection and Concealment of Spatially Defined Communication Networks. In: Genetic and Evolutionary Computation Conference, GECCO 2023, ACM Press (to appear).
• M. Stimson, W. Reid, A. Neumann, S. Ratcliffe, F. Neumann (2023): Improving Confidence in Evolutionary Mine Scheduling via Uncertainty Discounting, IEEE 2023 Congress on Evolutionary Computation
• Y. Xie, A. Neumann, T. Stanford, Ch. Rasmussen, D. Dumuid, F. Neumann: Evolutionary Time Use Optimization for Improving Children's Health Outcomes. In: Parallel Problem Solving from Nature, PPSN 2022.
• A. Nikfarjam, A. Neumann, F. Neumann (2022): Evolutionary Diversity Optimisation for The Traveling Thief Problem. In: Genetic and Evolutionary Computation Conference, GECCO 2022, ACM Press.
• A.Nikfarjam, A. Neumann, F. Neumann (2022): On the Use of Quality Diversity Algorithms for The Traveling Thief Problem. In: Genetic and Evolutionary Computation Conference, GECCO 2022, ACM Press.
• Y. Xie, A. Neumann, F. Neumann (2021): Heuristic Strategies for Solving Complex Interacting Stockpile Blending Problem with Chance Constraints. In: Genetic and Evolutionary Computation Conference, GECCO 2021, ACM Press.
• W. Reid, A. Neumann, S. Ratcliffe, F. Neumann (2021): Advanced mine optimisation under uncertainty using evolution. In: Genetic and Evolutionary Computation Conference, GECCO Companion 2021, ACM Press.
• Y. Xie, A. Neumann, F. Neumann (2021): Heuristic Strategies for Solving Complex Interacting Large-Scale Stockpile Blending Problems. In: Genetic and Evolutionary Computation Conference, GECCO 2021, ACM Press.