Correlation analysis between the comprehensive evaluation index of power supply reliability and influencing factors can provide effective evidence for power supply reliability promotion in a distribution network. First, the correlation influence coefficients are obtained through the correlation analysis of various power supply reliability indicators, and the comprehensive weight method combined with an analytic hierarchy process and improved entropy method are corrected by a correlation influence coefficient to determine comprehensive indicators. Second, a distance influence coefficient is introduced to overcome the shortcoming of traditional gray correlation analysis. Then the correlation degree of each influence factor is calculated to the comprehensive evaluation index and it is subsequently ranked. Finally, the actual data is used for verification, and the results show that the analysis method can effectively identify areas with weak power supply reliability and factors that have a greater impact on power supply reliability. This has a certain reference value for improving power supply reliability. This work is supported by the National Natural Science Foundation of Shanghai (No. 19ZR1420700) and the Local Capacity Building Project of Shanghai Science and Technology Committee (No. 18020500900).