<p>A multi-input single-output fuzzy neural network controller is presented for reducing the frequency oscillations of distributed generations, and minimise entire interconnected system production costs. Firstly, to satisfy the constraint of the cost function, the proportional-integral (PI) controller is used for economic dispatch. Secondly, the fuzzy neural network controller is designed to reduce frequency oscillations in the control process and meet cost constraints. At the same time, a genetic algorithm is adopted to amend controller parameters, thus improving the controller performance. The designed controller is distributed and can efficiently regulate the system over the entire range for overall optimization by simply obtaining messages from neighboring generators. The effectiveness of the proposed control strategy is validated through simulations conducted on the Hardware-in-the-Loop platform.</p>