The rapid adoption of electric vehicles (EVs) in recent years has led to a surge in power demand, presenting challenges in maintaining grid stability and efficiency. In response, service providers must integrate EVs with renewable energy sources while addressing the intermittent nature of distributed generation (DG) and fluctuating demand. Demand response management (DRM) offers a solution by aligning energy usage with renewable energy availability and optimising grid performance. Modern distribution systems advocate for the prediction of station usage and service availability to estimate charging demand. This research explores the use of a gated recurrent network (GRN) model for scheduling EV charging, with the goal of reducing peak demand. The integration of optimal DRM with DG further enhances the performance. The proposed scheduling algorithm incorporates DG‐DRM to predict charging needs and alleviate peak load in the IEEE 33‐bus system and the real‐time utility network (RTUN)‐17 bus test system. Consumer participation in DRM maximises the total social benefit by lowering generation costs and congestion indices. A heuristic GRN model, combined with a probability‐based incremental learning algorithm, is introduced to tackle multi‐objective optimisation. The algorithm is tested across various scenarios, with EV scheduling carried out in the first phase and DRM with DG parameters optimised in the second. The results show the algorithm's superior performance in achieving the objective function compared to other computational methods.