Optimisation de la consommation d’énergie d’un entrepôt frigorifique : une double approche par la recherche opérationnelle et l’apprentissage automatique
Cold storage in Europe consume important amounts of energy to maintain cold rooms at low temperatures. The cold production control method most commonly used in cold stores does not account for variations in the price of electricity caused by the fluctuating needs of the electrical network. The thermal inertia of the cold rooms as well as the coolant tank could be used as energy storage. Moreover, the compressors are often used at suboptimal production levels. Those practices lead to extra energy consumption costs.
In the present research work, two approaches are proposed to improve the control of cold stores. The first approach is based on the mathematical modelling of the cold stores, and by the application of optimisation algorithms to those models in order to generate energy consumption schedules with minimal cost. The second approach, based on machine learning techniques, aims at establishing the best production decision in a given context by predicting the future cost generated by each possible production decision. These two approaches are compared to the most common control method for cold stores.