Cloud computing lets people around the world use IT services through the internet. These services include running large programs for personal, scientific, and business purposes, and users pay based on how much they use. However, running the cloud takes a lot of energy because data centers, which host cloud programs, need powerful servers to handle the many requests they get every day. This results in high costs and a negative impact on the environment due to carbon emissions. In our research, we developed a new method to make cloud centers more energy-efficient. To reduce energy use and predict workloads, we combined fuzzy logic and neural networks. Furthermore, to optimize how virtual machines move throughout the cloud, we applied ant colony optimization, a technique inspired by how ants locate pathways. Our trials revealed that our solution outperforms others in terms of energy conservation and processing user demands. It decreased resource loss by 21.3% across 832 time periods while denying fewer requests, decreasing the rate by 5.6%. Finally, our technique was evaluated and discovered to be very accurate, forecasting energy usage with more than 96% accuracy.