lhw-kl's starred repositories
Two_Layer_EMS
Code for IEEE Transactions: A Two-Layer Energy Management System for Microgrids With Hybrid Energy Storage Considering Degradation Costs.
Autonomous_Guidance_MPC_and_LQR-LMI
Kinematic MPC and dynamic LPV-LQR state feedback control for an autonomous vehicle
Net-MPC_Collision-Avoidance
MATLAB Simulation of Networked Model Predictive Control for Vehicle Collision Avoidance
Autonomous-Drive
Autonomous Vehicle modelling using MATLAB and Simulink
NPBayesHMM
Nonparametric Bayesian Inference for Sequential Data. Includes state-of-the-art MCMC inference for Beta process Hidden Markov Models (BP-HMM). Implemented in Matlab.
matlab-hmm
Open source HMM toolbox, with Discrete-HMM, Gaussian-HMM, GMM-HMM. (matlab)
Energy_Systems_and_Control-Projects
Projects related to Energy Systems and Control covering Flight Path Optimization, Battery Modeling, State Estimation, Optimal Economic Dispatch of Distribution, Forecasting Electricity Power Consumption, Optimal PHEV Energy Management
admm-energy-management
An ADMM solver for energy management problems in plug-in hybrid electric vehicles
Simscape-HEV-Series-Parallel
Model of a parallel-series hybrid-electric vehicle with system-level and detailed variants of electrical system.
RenewableEnergyManagement
Renewable Energy Management and Demand Response and by PSO Algorithm (Matlab code)
Two-Stage-Stochastic-Optimization
Minimizing costs in reservoir storage systems has been a challenging problem over the years. Several methods have been used previously to solve this problem. This paper would be considering the Two-Stage Stochastic Programming technique in solving this problem but the objective function would be a quadratic function. This function is the squared difference between release and the demand. Risk is also considered in solving this problem and the results are benchmarked against that of the Fletcher-Ponnambalam method. The results are also compared to that of the deterministic solution and the case of perfect information. The Two-Stage Stochastic Programming applied to a quadratic objective function gave promising results. As the number of scenarios increased, the optimal value approached that of the FP method. The stochastic solution from the TSP was shown to give 16.8% improvement in costs compared to the deterministic solution and the results of EVPI showed that getting perfect information for our problem would be highly beneficial leading to an 86.7% reduction in cost over time.
Convex-Optimization
Generating collision-free trajectories in 3D space for multiple quadcopters within seconds by minimizing the total thrust at each time step for each quadcopter using Sequential Convex Programming (SCP). The goal is to transition from an initial to a final set of states, each consisting of position, velocity and acceleration. The vehicles must maintain a minimum distance between each other and satisfy other trajectory constraints.
reinforcement_learning_control_nnets_model
My undergraduate final project - Modeling and control of a distillation column using neural networks and reinforcement learning.
Spectral-RNN
Spectral RNNs with adaptive window learning in TensorFlow, ICANN 2020.
semester-thesis
Source code of my semester thesis "Chance-Constrained Programming for Autonomous Vehicles in Uncertain Environments", completed as part of my MSc studies at ETH Zurich.
arhmm_mcmc
Parallel MCMC sampling of AR-HMMs for stochastic time series prediction.
Hessian-Generator
MATLAB function to compute Hessian of a function
MultiGaussian-HMM
HMM with Multivate Gaussian distribution as Observation model
RoadOptimization
Project on optimization codes as per "Road Reference Profiles based on Optimization Routines for Connected and Automated Vehicles"
Autonomous_Guidance_MPC_and_LQR-LMI
Kinematic MPC and dynamic LPV-LQR state feedback control for an autonomous vehicle