This paper considers the representation of energy storage in electricity sector capacity planning models. The incorporation of storage in long-term systems models of this type is increasingly relevant as the cost of storage technologies, particularly batteries, and of complementary variable renewable technologies, decline. To value storage technologies appropriately, a representation of linkages between time periods is required, breaking classical temporal aggregation strategies that greatly improve computation time. We appraise approaches to address this problem, highlighting a common underlying structure, conditions for lossless aggregation, and challenges of aggregation at relevant geographical scales. We then investigate solutions to the modeling problem including a decomposition scheme to avoid temporal aggregation at a parallelizable computational cost. These examples frame aspects of the problem ripe for contributions from the operational research community.