This paper proposes a novel fuzzy control method based on the research of grey theory and switching algorithm in networked control systems (NCSs). A grey prediction structure is used to obtain more important information from remote sensors, and an on-line rule switching mechanism is constructed to provide an appropriate forecasting step size to the grey predictor. The overall mathematical model of this grey prediction based fuzzy controller is established. By using this method to get an appropriate positive or negative forecasting step size in NCSs, the random characteristic of some non-stationary time series from the sensors can be reduced so as to improve control performance. Experiments on a nonlinear plant via communication network show its precision and robustness is better than other traditional control methods.