Publications
-
Optimizing Comfort and Energy Efficiency: The Impact of Model Accuracy on Mutli-Objective MPC
Buildings are responsible for ∼30% of primary energy consumption, mainly because of Heating, Ventilation, and Air Conditioning (HVAC) systems. The usual ON/OFF controller tends to react to occupancy presence, causing discomfort and energy waste. Furthermore, these controllers usually focus on thermal comfort and disregard other comforts, such as air quality, visual, etc. due to their […]
-
Metaheuristics and Machine Learning Convergence: A Comprehensive Survey and Future Prospects
The integration of machine learning techniques with optimization algorithms has garnered increasing interest in recent years. Two primary purposes emerge from the literature: leveraging metaheuristics in machine learning applications such as regression, classification, and clustering, and enhancing metaheuristics using machine learning to improve convergence time, solution quality, and flexibility. Machine learning techniques offer real-time decision-making […]
-
Supply Chain Optimization with the Digital Twin: Case study of a warehouse
In a complex logistics landscape, the need for efficient and optimized Supply Chain’s (SC’s) is becoming increasingly important. This is crucial to creating an efficient SC and ensuring consistent, optimized use of resources. Efficient logistics management is essential if companies are to maintain their competitiveness in the marketplace. Digital technologies, such as digital warehouses, are […]
-
Industrial Process Optimization with Digital Twin Solutions: Modeling, Monitoring and Decision-Making. Application to a water filtration unit.
The digital transformation of industry is an essential pillar of the global economy, aimed at improving productivity, promoting sustainable development and optimizing industrial performance. It relies on the use of advanced technologies such as cyber-physical systems, artificial intelligence and the Internet of Things, which make industrial systems not only more complex, but also more communicative, […]
-
Medical Compression Prototype in a Wireless Sensor network
Medical Compression Prototype in a Wireless Sensor network (Submitted).
-
Ordonnancement d’atelier de production flexible sous incertitude du comportement humain
Ce travail traite de l’ordonnancement d’atelier de production flexible sous incertitude du comportement humain. Il met en avant l’importance de prendre en compte le comportement humain dans les systèmes de production modernes, notamment dans le cadre de l’Industrie 5.0. L’étude propose une modélisation du comportement humain via un processus de Markov, distinguant les états productifs […]
-
Ordonnancement résilient d’un atelier de type job shop flexible
Ce travail traite de l’optimisation de l’ordonnancement en milieu industriel en intégrant des aspects humains et environnementaux. Le premier document explore l’impact du comportement humain imprévisible sur la productivité d’un atelier flexible, en modélisant les travailleurs avec un processus de Markov et en optimisant leur affectation via un modèle mathématique non linéaire. Le second document […]
-
Effet de la complexité du réseau LSTM sur l’explicabilité en Maintenance Prédictive
La nature complexe des données en maintenance prédictive impose souvent l’utilisation de modèles d’apprentissage profonds. Malgré leur efficacité dans la prédiction du RUL (durée de vie résiduelle des machines), ces « boites noires » fournissent des résultats qui ne sont pas directement compréhensibles. Ainsi, des méthodes XAI post hoc sont gé néralement utilisées pour les […]
-
Hyperparameter Impact on Computational Efficiency in Federated Edge Learning
The heterogeneity induced by the federated edge learning execution environment poses many performance challenges. Indeed, a balance between efficient resource usage and inference accuracy must be found. Our work therefore aims at characterizing the hyperparameter influence by creating a variety of simulated execution circumstances. We designed an experimentation platform to simulate the execution of a […]
-
Optimizing Shapley Value for Client Valuation in Federated Learning through Enhanced GTG-Shapley
In the ever-evolving realm of federated learning (FL), the question of data worth resonates with newfound urgency across organizations and individuals. In the dynamic FL ecosystem, where data resides across distributed nodes, evaluating the value of each client’s data is paramount. The evaluation mechanism helps to understand individual contributions to the overall process and incentivizes […]
-
FedLbs: Federated Learning Loss-Based Swapping Approach for Energy Building’s Load Forecasting
Federated Learning (FL) is rapidly growing in popularity as a decentralized approach and is being adopted in smart building systems and energy forecasting without accessing sensitive data. Specifically, clients train their models using their own data. After that, only their model parameters are sent to the central server, which aggregates them by averaging the weights […]
-
Empowering Energy Consumption Forecasting in Smart Buildings: Towards a Hybrid Loss Function
Energy consumption forecasting is of paramount importance in achieving energy conservation goals. While numerous approaches have been developed to optimize building energy usage, predictive analytics stands out as a cornerstone tool for informed decision-making. Deep learning models have gained popularity for forecasting energy consumption in smart buildings. These models leverage a variety of techniques, including […]
Loading…
Erreur : tout le contenu a été chargé.