This paper presents a method for the detection and classification of complex power quality (PQ) disturbances using discrete wavelet transform (DWT) based ruled decision tree. The power quality disturbances are generated with the help of MATLAB using the mathematical relations as per IEEE Standard-1159. The investigated PQ disturbances include various combinations of voltage sag, voltage swell, momentary interruption, harmonics, oscillatory transient and impulsive transient. These power quality signals are decomposed using discrete wavelet transform with db4 as mother wavelet up to level 4 of decomposition. The detail coefficients and approximation coefficients are used for recognition of complex PQ disturbances. The features extracted from plots of these coefficients are given as input to the rulebased decision tree for classification of complex PQ disturbances. The effectiveness of proposed algorithm has been established by testing 30 data sets of each complex PQ disturbance obtained by varying the parameters.