With the continuous growth of mobile devices, due to the mobility of mobile devices, mobile user-s job requests are highly dynamic and unpredictable, and also user-s mobility is a key challenge in resource scheduling. Resource scheduling in edge computing has gained attention in research works because it is the key to the success of edge computing systems. Even though the cloud has many computations without exchanging data, but fails to meet the high requirements of users in real-time response due to the bandwidth congestion and lower energy consumption. Nevertheless, edge computing empowers cloud leverage to offload computing services from the cloud to the edge to improve the QoE of users. Thus, Federated learning, known as collaborative learning, is a machine learning technique that trains resource scheduling algorithms on multiple distributed edge devices or servers regardless of exchanging the local data samples in the environment.