The variable and unpredictable output from distributed generation (DG) like wind and solar creates new reliability concerns for distribution networks. Integrating DG on a large scale can unbalance the power supply and compromise quality, making accurate reliability assessment essential. This paper puts forward a new assessment method using a Transformer network. The method first utilizes an improved minimum path algorithm designed for grids with DG. This algorithm models the scenario where a section of the grid, if cut off from the main supply, can form an operational island, using its local DG to power essential loads. Secondly, the Transformer network is innovatively applied to classify reliability indices into specific intervals, transforming a difficult prediction challenge into a more manageable classification task. This overcomes the problem of non-smoothness in reliability data. We demonstrate the method’s effectiveness on Feeder 4 of the IEEE RBTS 6-node test system. The proposed framework enables dynamic monitoring and proactive warnings against operational risks in the grid.