Effective Visualisation of the High-Dimensional Pareto-Optimal Solutions

Visualising the Pareto-optimal solutions and their objectives can be challenging, more so when the number of objectives is large. The paper proposed the combined use of clustering and parallel coordinates plots to visualise the Pareto-optimal solutions. The trade-off surface is first segmented using a clustering algorithm, and parallel coordinates plots are then used to visualise the resulting set of Pareto-optimal designs. The paper described the analysis from the waste heat recovery system optimisation commonly found in the food and drinks process industries, comprising of a desuperheater coupled to a hot water reservoir. The system was parameterised, considering typical objectives, and MOEA was used to approximate the Pareto-optimal designs. The proposed visualisation was used to better understand the sensitivity of the system's parameters and their trade-offs, providing another source of information for prospective installations. Original publication: M. Mokhtar, S. Burns, D. Ross, and I. Hunt, Exploring Multi-Objective Trade-Offs in the Design Space of a Waste Heat Recovery System, Applied Energy, Elsevier, Vol. 195, 1 June 2017, Pages 114--124