Clemente, A. V., Giljarhus, K. E. T., Oggiano, L., & Ruocco, M. (2024). Rapid pedestrian‐level wind field prediction for early‐stage design using Pareto‐optimized convolutional neural networks. Computer‐Aided Civil and Infrastructure Engineering, 39(18), 2826-2839.
Traditional computational fluid dynamics (CFD) methods used for wind field prediction can be time-consuming, limiting architectural creativity in the early-stage design process. Deep learning models have the potential to significantly speed up wind field prediction. This work introduces a convolutional neural network (CNN) approach based on the U-Net architecture, to rapidly predict wind in simplified urban environments, representative of early-stage design. The process of generating a wind field prediction at pedestrian level is reformulated from a 3D CFD simulation into a 2D image-to-image translation task, using the projected building heights as input.
Traditional computational fluid dynamics (CFD) methods used for wind field prediction can be time-consuming, limiting architectural creativity in the early-stage design process. Deep learning models have the potential to significantly speed up wind field prediction. This work introduces a convolutional neural network (CNN) approach based on the U-Net architecture, to rapidly predict wind in simplified urban environments, representative of early-stage design. The process of generating a wind field prediction at pedestrian level is reformulated from a 3D CFD simulation into a 2D image-to-image translation task, using the projected building heights as input. Testing on standard consumer hardware shows that our model can efficiently predict wind velocities in urban settings in less than 1 ms. Further tests on different configurations of the model, combined with a Pareto front analysis, helped identify the trade-off between accuracy and computational efficiency. The fastest configuration is close to seven times faster, while having a relative loss, which is 1.8 times higher than the most accurate configuration. This CNN-based approach provides a fast and efficient method for pedestrian wind comfort (PWC) analysis, potentially aiding in more efficient urban design processes.
Clemente, A. V., Nocente, A., & Ruocco, M. (2023). Global Transformer Architecture for Indoor Room Temperature Forecasting. Journal of Physics: Conference Series, 2600(2), 022018. https://doi.org/10.1088/1742-6596/2600/2/022018
A thorough regulation of building energy systems translates in relevant energy savings and in a better comfort for the occupants. Algorithms to predict the thermal state of a building on a certain time horizon with a good confidence are essential for the implementation of effective control systems. This work presents a global Transformer architecture for indoor temperature forecasting in multi-room buildings, aiming at optimizing energy consumption and reducing greenhouse gas emissions associated with HVAC systems.
A thorough regulation of building energy systems translates in relevant energy savings and in a better comfort for the occupants. Algorithms to predict the thermal state of a building on a certain time horizon with a good confidence are essential for the implementation of effective control systems. This work presents a global Transformer architecture for indoor temperature forecasting in multi-room buildings, aiming at optimizing energy consumption and reducing greenhouse gas emissions associated with HVAC systems. Recent advancements in deep learning have enabled the development of more sophisticated forecasting models compared to traditional feedback control systems. The proposed global Transformer architecture can be trained on the entire dataset encompassing all rooms, eliminating the need for multiple room-specific models, significantly improving predictive performance, and simplifying deployment and maintenance. Notably, this study is the first to apply a Transformer architecture for indoor temperature forecasting in multi-room buildings. The proposed approach provides a novel solution to enhance the accuracy and efficiency of temperature forecasting, serving as a valuable tool to optimize energy consumption and decrease greenhouse gas emissions in the building sector.
Alfredo, C. (2017). Decoupling deep learning and reinforcement learning for stable and efficient deep policy gradient algorithms [Master's thesis, Norwegian University of Science and Technology].
This thesis explores the exciting new field of deep reinforcement learning (Deep RL). This field combines well known reinforcement learning algorithms with newly developed deep learning algorithms. With Deep RL it is possible to train agents that can perform well in their environment, without the need for prior knowledge. Deep RL agents are able to learn solely by the low level percepts, such as vision and sound, they observe when interacting with the environment.
This thesis explores the exciting new field of deep reinforcement learning (Deep RL). This field combines well known reinforcement learning algorithms with newly developed deep learning algorithms. With Deep RL it is possible to train agents that can perform well in their environment, without the need for prior knowledge. Deep RL agents are able to learn solely by the low level percepts, such as vision and sound, they observe when interacting with the environment. Combining deep learning and reinforcement learning is not an easy task, and many different methods have been proposed. In this thesis I explore a novel method for combining these two techniques that matches the performance of a state of the art deep reinforcement learning algorithm in the Atari domain for the game of Pong, while requiring fewer samples.
Alfredo, C., Humberto, C., & Arjun, C. (2017). Efficient parallel methods for deep reinforcement learning. In The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (pp. 1-6).
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time.
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-policy experiences and employing synchronous updates. Our algorithm achieves state-of-the-art performance on the Atari domain after only a few hours of training. Our framework thus opens the door for much faster experimentation on demanding problem domains. Our implementation is open-source and is made public at this https URL