Cell free massive MIMO (CF mMIMO) systems are a promising solution to enhance the performance in 6G wireless networks. Its distributed nature of the architecture makes it highly reliable, provides sufficient coverage and allows higher performance than cellular networks. Energy efficiency (EE) is an important metric that reduces the operating costs and also better for the environment. In this work, we optimize the downlink EE performance with maximum ratio transmission (MRT) precoding and power allocation. Our aim is to achieve a less complex, distributed and scalable solution. To achieve this, we apply unsupervised machine learning (ML) with permutation equivariant architecture and use a non-convex objective function with multiple local optima. We compare the performance with the centralized and computationally expensive sequential convex approximation (SCA). The results indicate that the proposed approach can outperform the baseline with significantly less computation time.