Abstract This paper reports an investigation of the thermal performance of an energy storage heat sink incorporated with multiple phase change materials (PCMs). A six-cavity cylindrical heat sink heated at the base is chosen for the investigations with Docosane, n-Eicosane, and Tetracosane as candidate PCMs. The phase transition of PCMs has been visualized with a digital camera and three-dimensional numerical simulations. The results show that the latent heat exploitation process of PCMs in a heat sink with multiple PCMs is different from the single PCM heat sink, where the PCMs in all cavities melt distinctly rather at a time, thereby opening up windows for obtaining deeper insights that can lead to better performing heat sinks. A trained artificial neural network (ANN) with 78 representative heat sink configurations based on the arrangement of the PCMs in the cavities as input and charging and discharging times as output is used to swiftly drive the optimization engine. Finally, multi-objective optimization is performed using the artificial bee colony algorithm with simultaneous consideration of two conflicting objectives (i.e., maximizing charging cycle time and minimizing discharging cycle time) of the heat sink. From the optimization study, best performing nondominated Pareto optimal heat sink configurations are obtained and validated with the in-house experimental results. From the investigations, it is found that the heat sink configurations with multiple PCMs perform on par with the single PCMs in the charging process and show a superiority of up to 24% in discharging process over a heat sink with single PCMs in terms of time to reach set point temperature.