Qualitative-evolutionary design of greenhouse environment control agents

A novel technique that fuses qualitative reasoning and evolutionary computation in the design of control agents for the control of the environment of a greenhouse is proposed in this paper. Linguistic rules relate the attributes of the greenhouse performance in response to perturbations in the desired set points to the suitability of the agent. Defuzzification of the fuzzy suitability membership function yields a quantitative measure of the fitness of the agent to satisfy the system performance specifications. The fitness measure is used in a genetic algorithm that performs a stochastic search for the global optimum parameters of the agent.