Project "Development of Federated learning algorithm for Intelligent Mobility Management System using SUMO simulation with Python Language

My goal is to develop two different Federated learning algorithms(weighted average, federated average) for an Intelligent Mobility Management System using SUMO simulation with Python Language. I have experience and knowledge of SUMO simulation with Python language, and can provide a high-level overview of the proposed Federated learning algorithm. My understanding of the applications of the Intelligent Mobility Management System is that it can be used for 1.Traffic prediction, 2.Signal control (traffic light management), and 3.Route optimization. I am looking for a detailed level of detail for the Federated learning algorithm, including detailed pseudocode to help ensure its successful implementation. The performance metrics graphs are 1.Accuracy and loss of training (train)/validation (val) with server-trained model over the epoch rounds and federated learning model over the communication rounds. 2.Flow of traffic over the simulation time(sec) 3. Route planning/selection on the road with the shortest traveling time 4.Traffic speed/flow prediction performance over MAE, MSE, RMSE, MAPE, R-squared and some other relevant graphs.
Federated Learning Project Implementation Link for your reference:
https://towardsdatascience.com/federated-learning-a-step-by-step-implementation-in-tensorflow-aac568283399
https://flower.dev/docs/tutorial/Flower-1-Intro-to-FL-PyTorch.html
GitHub - litian96/FedProx: Federated Optimization in Heterogeneous Networks (MLSys '20)
https://www.youtube.com/watch?v=CvO6T1UMmOo&t=317s
https://github.com/PacktPublishing/Federated-Learning-with-Python