A quantitative maintenance policy development framework for a fleet of self-service systems

Self-service systems, such as electric vehicle charging piles (EVCPs), are commonly deployed in fleets without on-site personnel. To handle service failures, frequent and thorough maintenance can be conducted to ensure a high service level, but it may also result in significant maintenance costs. Apparently, balancing the service level (and consequently, the revenue) with maintenance costs is essential for operators aiming to maximize their profit. However, achieving this balance is challenging and underexplored due to the inherent and unique characteristics of self-service systems. In this paper, we present a quantitative maintenance policy development framework to maximize the long-term profit rate of a fleet of self-service systems. First, we introduce a novel three-dimensional maintenance policy that optimizes the timing and level of maintenance actions. Next, we develop a triple-layer model to characterize the fleet's state transition, considering the fleet's behavior within demand arrival cycles, across demand arrival cycles, and across maintenance epochs. We also define important metrics and study their properties for assessing the service level and profit rate of the fleet. To facilitate policy optimization, we develop a Kriging-based optimization algorithm capable of efficiently solving the associated mixed-integer nonlinear optimization problem with a vast search space. Finally, we offer several managerial implications for identifying applicable scenarios for the proposed maintenance policy and assessing the impact of crucial parameters on both maintenance policy and profit. A fleet of eight EVCPs in Hong Kong is studied to illustrate how the proposed quantitative framework and these managerial implications assist the operator in enhancing their profitability.