In this paper we propose a fuzzy logic implementation of random early detection (RED) mechanism. The main objective of the proposed fuzzy controller is to reduce the loss probability of the RED mechanism without any change in channel utilization. Using fuzzy logic capabilities, we try to dynamically tune the loss probability of RED gateway. To achieve this goal, we use a two-input-single-output fuzzy controller. The inputs of fuzzy controllers are: 1) the error signal e1 which represents the difference between average queue size and a target point. 2) The error signal e2, which is calculated as the difference between the estimated value of incoming data rate and the target link capacity. The output of fuzzy controller is used to dynamically tune the max p parameter of RED gateway. All simulation results show that the proposed fuzzy mechanism has better performance than traditional RED and adaptive RED (ARED) mechanisms.