Building operations account for approximately 40% of US energy use and carbon emissions@ and vapor compression cycles are the primary method by which refrigeration and airconditioning systems operate. Representing a significant portion of commercial and residential building energy consumption@ vapor compression cycles are a target for improvement in efficiency and savings. This paper presents a data-driven approach to find the optimal operating conditions of single- and multievaporator systems to minimize energy consumption while meeting operational requirements such as constant cooling or constant evaporator outlet temperatures. Theproblemliesinthedevelopmentofacontrolarchitecturethat will minimize the energyconsumedwithout requiringanymodels of the system or expensive mass flow sensors. The application of the presented approach improves efficiency and is demonstrated in simulation and on an experimental system.