A Note on Cost Constrained Cultivation Management using Sensors

There is a lot of previous research on cultivation management based on mathematical engineering. In some previous research, the expected profit of cultivation management using sensors is maximized under the condition that growing states are unknown. Considerations of cost constraints are needed in real agriculture. But in the previous research, cost constraints are not considered. So, in this research, cost constrained cultivation management using sensors is studied. A new cultivation management method which maximizes the expected profit of cost constrained cultivation management using sensors is proposed. In the proposed method, multiple agricultural fields are managed. The cultivation management problem is modeled by Markov decision processes as previous research. The expected profit is maximized with reference to a Bayes criterion using dynamic programming method. The effectiveness of the proposed method is shown by some computational examples. Adaptive cultivation action selection, cost adjustment on the time axis and cost adjustment between the agricultural fields are confirmed in the computational examples.