Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms
It addresses the lack of renewable energy integration control in the dairy sector, offering a practical solution for farm energy management.
The paper proposes a two-layer multi-objective control system using differential evolution and multi-agent deep reinforcement learning for battery management in dairy farms, achieving up to 18% higher profits from energy arbitrage compared to rule-based models while complying with grid voltage limits.
The dairy industry in Ireland has a large potential for the integration of renewable energy and the reduction of carbon emissions. However, researchers of distributed generation control are mainly focused on residential and commercial applications. To contribute to the effective integration of renewable energy in the dairy sector, this paper presents a multi-objective optimisation control system based on differential evolution and multi agent Deep Reinforcement Learning. The proposed control is organised in two layers: the upper layer uses dynamic pricing, and the lower layer is based on multi-agent reinforcement learning for battery management. This paper also simulates the electrical response of the proposed control system in a rural distribution circuit. The simulation results show that the proposed control framework can improve profits from energy arbitrage up to 18% compared to using Rule-based models, increase the use of distributed generation without significantly increasing cost, and comply with the Irish grid code in terms of voltage variation.