Decision Support for Power Plant Shift Configuration Using Stochastic Simulation

Abstract

Power generation companies have to ensure a secure supply of power to their customers at any time. Hence, this particular application context implies a special feature of shift planning where a very robust solution of assignment is needed. In daily business this means all business functions have to be staffed competently at any time, otherwise a smooth power plant operation cannot take place. In this regard, optimal shift assignment is a highly important and complex task, where reliability is prioritized with respect to all other criteria, e.g. employee's interests. In order to test a shift configuration on operational level, we conceptualise a reactive framework to support tactical decision making. The concept switches between optimisation and stochastic simulation which takes uncertainty associated with employee sickness into account. An exemplary case study with realistic data of a power generation company analyses the operational consequences of uncertain absences on the performance of a given shift configuration.