20 February 2020 in Mathematical Programming Computation
24 June 2016 in IEEE Transactions on Power Electronics
Common approaches for direct model predictive control (MPC) for current reference tracking in power electronics suffer from the high computational complexity encountered when solving integer optimal control problems over long prediction horizons. We propose an efficient alternative method based on approximate dynamic programming, greatly reducing the computational burden and enabling sampling times below 25 μs. Our approach is based on the offline estimation of an infinite horizon value function, which is then utilized as the tail cost of an MPC problem. This allows us to reduce the controller horizon to a very small number of stages, while simultaneously improving the overall controller performance. Our proposed algorithm was implemented on a small size FPGA and validated on a variable-speed drive system with a three-level voltage-source converter. Time measurements showed that our algorithm requires only 5.76 μs for horizon N = 1 and 17.27 μs for N = 2, in both cases outperforming state-of-the-art approaches with much longer horizons in terms of currents distortion and switching frequency. To the authors' knowledge, this is the first time direct MPC for current control has been implemented on an FPGA solving the integer optimization problem in real time and achieving comparable performance to formulations with long prediction horizons.
1 July 2022 in INFORMS Journal on Computing
We propose a method to approximate the solution of online mixed-integer optimization (MIO) problems at very high speed using machine learning. By exploiting the repetitive nature of online optimization, we can greatly speed up the solution time. Our approach encodes the optimal solution into a small amount of information denoted as strategy using the voice of optimization framework. In this way, the core part of the optimization routine becomes a multiclass classification problem that can be solved very quickly. In this work, we extend that framework to real-time and high-speed applications focusing on parametric mixed-integer quadratic optimization. We propose an extremely fast online optimization method consisting of a feedforward neural network evaluation and a linear system solution where the matrix has already been factorized. Therefore, this online approach does not require any solver or iterative algorithm. We show the speed of the proposed method both in terms of total computations required and measured execution time. We estimate the number of floating point operations required to completely recover the optimal solution as a function of the problem dimensions. Compared with state-of-the-art MIO routines, the online running time of our method is very predictable and can be lower than a single matrix factorization time. We benchmark our method against the state-of-the-art solver Gurobi obtaining up to two to three orders of magnitude speedups on examples from fuel cell energy management, sparse portfolio optimization, and motion planning with obstacle avoidance. Summary of Contribution: We propose a technique to approximate the solution of online optimization problems at high speed using machine learning. By exploiting the repetitive nature of online optimization, we learn the mapping between the key problem parameters and an encoding of the optimal solution to greatly speed up the solution time. This allows us to significantly improve the computation time and resources needed to solve online mixed-integer optimization problems. We obtain a simple method with a very low computing time variance, which is crucial in online settings.
17 March 2021 in IEEE Journal of Biomedical and Health Informatics
Heart-related anomalies are among the most common causes of death worldwide. Patients are often asymptomatic until a fatal event happens, and even when they are under observation, trained personnel is needed in order to identify a heart anomaly. In the last decades, there has been increasing evidence of how Machine Learning can be leveraged to detect such anomalies, thanks to the availability of Electrocardiograms (ECG) in digital format. New developments in technology have allowed to exploit such data to build models able to analyze the patterns in the occurrence of heart beats, and spot anomalies from them. In this work, we propose a novel methodology to extract ECG-related features and predict the type of ECG recorded in real time (less than 30 milliseconds). Our models leverage a collection of almost 40 thousand ECGs labeled by expert cardiologists across different hospitals and countries, and are able to detect 7 types of signals: Normal, AF, Tachycardia, Bradycardia, Arrhythmia, Other or Noisy. We exploit the XGBoost algorithm, a leading machine learning method, to train models achieving out of sample F1 Scores in the range 0.93 0.99. To our knowledge, this is the first work reporting high performance across hospitals, countries and recording standards.
19 July 2020 in Machine Learning
16 December 2021 in IEEE Robotics and Automation Letters
Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex program (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a logical strategy , which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.