<p>The adaptive systems of managing the microgrid are required for the integration of sources of renewable energy and to counteract the demand in the resilience of energy. In the meantime, the recent techniques has drawbacks of utilizing the resources inefficiently, distribution of power in imbalance manner, and the adaptability is limited for the conditions of demand and supply dynamically. For addressing such issues this research is carried out for trading of energy in the smart microgrid through an Equilibrium System of Hopfield with Decision Nash (DNEHNS). The suggested approach combines the mechanism of fairness equilibrium Nash with the neural network of Hopfield for providing the decisions of trading in balanced and in efficient manner. The key parameters considered in the training includes price in market, demand of load, losses in energy and the consistency in the supply for prioritizing the allocation of energy. The demonstration of the analytical results provides that the performance of the DNEHNS has been enhanced in a significant manner in correlation with the existing techniques. The suggested model has a determination coefficient of 99.85%, the enhancement form the existing models was about 9% with the reduction in the time of computation as 10.36%. In addition to that, the metrics of error are lower with the indication of stability, prediction and accuracy as higher. These performance metrics have confirmed that the suggested technique is a fair and efficient manner of trading for large scalable smart energy microgrids. The extended research will focus on the system of grid on the large scale interconnections.</p>