Update README.md

README.md

@@ -52,35 +52,61 @@ able, data-driven HVAC control.
 
 # We devided this entire project into 4 phases. Please go through each step to use our system.
 
-### Energy Plus Setup and Trajectory Data generation
-
-## System Requirements
+### Energy Plus Setup
+For this project we use Sinergym and energy plus. sinergym has also a prebuilt docker version. you can use this and for installation:
+```bash
+docker pull ghcr.io/ugr-sail/sinergym:2.4.0
+```
 
-- Ubuntu 22.04 (recommended)
-- Python ≥ 3.10
-- EnergyPlus ≥ 25.x
-- CUDA (optional, for GPU training)
-## Install Dependencies
+After this run the docker container and see next steps
 
 ```bash
-# Create environment
-python -m venv genhvac_env
-source genhvac_env/bin/activate
-
-# Install required packages
-pip install torch torchvision torchaudio
-pip install gymnasium
-pip install sinergym
-pip install stable-baselines3
-pip install pandas numpy matplotlib tqdm
+docker run -it \
+  --name genhvac_container \
+  -v $(pwd):/workspace \
+  ghcr.io/ugr-sail/sinergym:2.4.0 \
+  /bin/bash
 ```
+### Data generation
+We have provided utils files which are being used at all three instances: Data generation, training and inference. 
+
+use the data generation script along with rollout runner to generate sequential data. 
+
+Our architecture works with all kinds of policy and you can try different patterns for generating data. If you have ecobee data then that can work too. if you have MPC rules for
+a particular building model then it will work excellent. This works a framework for data generation.
+
+We have rollouts which you can use to generate specific building location data or building type or combine different envolop locations and weather and building type.
+
+### Training Phase
+
+After you have generated data you can move on to the training phase which , for our experiments we generted more than 2300 sequential data combinations and resulted in more than 3 million trajectories.
+
+Training phase is devided into 3 parts Dataloader, decision transformer and losses and finally the main training code.
+
+The only changes needed will be mapping of the observation data from the sensors and also the action keys. We have already done that for a office small STD2013 and Office Medium STD2013. The same architecture
+can be extended to other buildings in the HOT data set and also with the ecobee data set as well as any real building dataset.
+
+Next comes the training code. We tried to make a system which can a be framed as a general zero shot system. However the novelty also lies in the entire system since this system can be extended
+to cover vast amount of data atleast 1000 to 10000 times more. In the training code you have to simply increase the size of the transformer model and our losses and embeddings layers will 
+try to generalize over more and more buildings residential homes etc.
+
+We condition on different RTG for comfort and energy savings. Anykind of data will already be filtered on different RTG and TOPK filtering helping model to understand what kind of 
+actions lead to what kind of consequenses.
+
+5) LLM deployment phase
+
+One of the main high lights of our System is LLM and digital human in the loop which is possible because of flexible RTG conditioning posible because of transformer architecture.
+Different RTG can lead to different sequences which is completely different approach where we give control to LLM and because of that we never face sudden uneven temperature settings.
+
+For LLM utilisation please download and setup OLLAMA 
 
-  
+For this experiments we used several opensource Quantized versions of both resonsing and non reasoning LLMS liek DEEPseek V1 and r1 lamma, etc. 
+you have to create the llm client and server setup which is provided in the llm folder. 
 
-3) Training Phase
+Our system use LLM to capture the humnistic value of the human behaviour so you can change or tweak the prompt as per your behaviour or create your own personal digital persona.
 
-4) LLM deployment phase
+After this you have to move on to the inference Server side to tie up all these together
 
-5) Inference 
+7) Inference 
 
-6) Deployment on a real building using cloud server and edge device
+8) Deployment on a real building using cloud server and edge device