energy-efficient

Multi-objective Flexible Job Shop Scheduling Problem with transportation constraint solved with NSGA-II, VNS and improved initialisation

Source code for the paper "Energy-Efficient Client Sampling for Federated Learning in Heterogeneous Mobile Edge Computing Networks", this paper is pulished in ICC 2024.

Prediciton of loads in data centers using Machine Learning (ML) Models

Adaptive Sparse Training (AST): 92.1% ImageNet-100 accuracy with 61% energy savings and zero degradation. Production-ready implementations for energy-efficient deep learning with ResNet50 and modern architectures.

Auto Solar Street Light Controller – LDR and IR-based energy-efficient lighting system with comparator and relay logic (2018-19)

SM² Coin core library

Rewind — Premier SDK de calcul nativement reversible pour Rust. Debugger temporel, portes Toffoli, types lineaires. Information is Sacred.

Adaptive screen brightness & sound auto-control for Linux and Windows — smooth transitions, ambient-aware, zero-touch

TachyonSort is the fast constrained unstable sort.

An energy-efficient TinyML fall detector that runs entirely on an Arduino Nano 33 BLE Sense. A cascaded pipeline keeps the CNN idle during everyday motion and runs it only on likely fall events, cutting per-event energy by about 98 percent versus an always-on model.

A novel research framework combining Hierarchical RL (A2C + PPO), Meta-Learning (Reptile), and SHAP Explainability for adaptive, interpretable, energy-efficient cloud scheduling — trained on real Google and Alibaba cluster traces.

Escaping the SaaS trap: Building an independent, energy-efficient home server on refurbished hardware.

MATLAB simulation and implementation of an H∞/LMI-based energy-aware consensus controller for multi-agent systems.

Bio-inspired sparse spiking neural network: near-lossless accuracy at 2 orders of magnitude lower energy, built from real Drosophila connectome statistical laws

NeutrinoSort is the fast constrained stable sort.

Chinese Building Energy-Efficient Design Datasets

Novel blockchain consensus mechanism replacing energy-intensive mining with productive federated learning. Miners collaborate to train AI models, with winners selected through democratic voting.

Energy Efficient CPU Scheduling Algorithm in Operating System

Hierarchical multi-edge federated learning framework with adaptive client selection for privacy-preserving and energy-efficient healthcare.