At temperatures higher than 5 ^oC in the cooling chamber of refrigeration systems, bacteria multiply rapidly on fresh fishes, thereby leading to an increased risk of foodborne diseases. Maintaining the storage temperature within the recommended bounds of 0^oC and 5^oC is needed to maintain food safety and qualty. This study presents model predictive control of a data-driven medium-temperature cold storage system using a subspace system identification technique. The identified linear model presents a holistic view of the whole system, with each subsystem cohesively linked together. The data-driven model was developed from synthetic data derived from a high-fidelity simulation benchmark model of a supermarket refrigeration system from Aalborg University, Denmark. The benchmark model consists of a medium-temperature closed display case, the suction manifold and the compressor rack. The data on the expansion valve, suction pressure, compressor capacity, heat transfer rate and ambient temperature were taken as inputs, while the data on the air and goods temperatures were taken as outputs based on expert knowlege. A linear model predictive controller was designed to control the temperature outputs of the identified linear model, and the outputs were compared with the proportional–integral dead band control used in the benchmark. Simulation results for 24 hours show that the model predictive controller was able to achieve an air temperature and a goods temperature within the recommended temperature range of 0 ^oC and 5 ^oC that guarantees safe storage of fresh fishes. These results imply that a reduced-order model of a commercial refrigeration system that is robust, reliable and stable can be developed and controlled to achieve the goal of food safety, thereby guaranteeing food security and reducing costs.