Abstract
Increasing profit is desired in Japanese agriculture. There is many previous research on profit maximization in agriculture. In a previous research crop rotation problem and cultivation management problem are solved as one integrated management problem in order to maximize the profit in agriculture. In the previous research the profit is maximized under the condition that growth states are known. But in smart agriculture with sensors the true growth states are unknown. In this research a new integrated management method for smart agriculture with sensors is proposed. The proposed method maximizes the profit under the condition that the growth states are unknown using Markov decision processes. The effectiveness of the proposed method is shown by some simulation examples. The profit of the proposed method is greater than that of the comparison target. In the results of the proposed method the adaptive selection according to the fluctuating crop price was confirmed. The proposed method is expected to contribute to the automation of decision making in smart agriculture. This research is a basic research, and future extended research is required.
