Intelligent Control Strategy of a Battery Energy Storage for a Climate‐Controlled Greenhouse with a High Proportion of Local Renewable Energy

Greenhouse cultivation offers the advantage of controlled growth conditions, leading to enhanced crop productivity and quality. However, maintaining these optimal conditions requires substantial energy, resulting in increased greenhouse gas emissions and operational costs. Integrating local renewable energy sources, particularly photovoltaic (PV) solar energy, has demonstrated the potential to reduce energy consumption and costs. This paper proposes a machine learning‐based intelligent control strategy for greenhouses using a solar photovoltaic system combined with battery energy storage system (BESS). Long short‐term memory (LSTM) forecasting models are developed to forecast power consumption and solar PV production. The outputs of these forecasting models are then fed into a reinforcement learning (RL)‐based battery control model. This control model is trained to minimize energy costs by taking advantage of variable electricity spot prices and reducing peak energy consumption. The performance of the proposed system is evaluated with actual operational data. Results show that the proposed model reduces variable charges by 2.2% and 2.7% and decreases peak energy consumption by 24% and 19% in February and March 2023, respectively. Overall, the proposed system demonstrated the potential to utilize local renewable energy, minimize operational costs, and achieve a sustainable energy balance.