SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Explore the source record for details and available documents.
This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem. We then propose a novel on-policy MARL algorithm, PowerNet, in which each agent (DG) learns a control policy based on (sub-)global reward but local states and encoded communication messages from its neighbors. Motivated by the fact that a local control from one agent has limited impact on agents distant from it, we exploit a novel spatial discount factor to reduce the effect from remote agents, to expedite the training process and improve scalability. Furthermore, a differentiable, learning-based communication protocol is employed to foster the collaborations among neighboring agents. In addition, to mitigate the effects of system uncertainty and random noise introduced during on-policy learning, we utilize an action smoothing factor to stabilize the policy execution. To facilitate training and evaluation, we develop PGSim, an efficient, high-fidelity powergrid simulation platform. Here, experimental results in two microgrid setups show that the developed PowerNet outperforms the conventional model-based control method, as well as several state-of-the-art MARL algorithms. The decentralized learning scheme and high sample efficiency also make it viable to large-scale power grids.
Classical and advanced hybridization methods are employed in the control literature to calibrate the tuning parameters of internal model control (IMC) and proportional-integral-derivative (PID) controllers. This paper presents an alternative tuning design for the generalized predictive controller (GPC) that is based on both the positional process model and cost function. The proposed method involves the selection of an integral polynomial weighting filter for reference and output signals to deal with reference tracking, disturbance rejection, model-plant mismatch (MPM), minimum control energy and closed-loop robustness. The filter positional GPC (FP-GPC) obtained is transformed into a two-degree-of-freedom polynomial filtered RST structure and then into filtered internal model control (F-IMC) and PID controllers. Also, a multi-objective optimization based on genetic algorithm is applied to tune the filter parameters. Numerical and experimental essays show the effectiveness of the proposed control methodology.
Power system algorithms such as AC optimal power flow and coordinated volt/var control of the bulk power system are computationally intensive and become difficult to solve in operational time frames. The computational time required to run these algorithms increases exponentially as the size of the power system increases. The solution time for multiple subsystems is less than that for solving the entire system simultaneously, and the local nature of the voltage problem lends itself to such decomposition. This paper describes an algorithm that can be used to perform power system decomposition from the point of view of the voltage control problem. Our approach takes advantage of the dominant localized effect of voltage control and is based on clustering buses according to the electrical distances between them. One of the contributions of the paper is to use multidimensional scaling to compute n-dimensional Euclidean coordinates for each bus based on electrical distance to perform algorithms like K-means clustering. A simple coordinated reactive power control of photovoltaic inverters for voltage regulation is used to demonstrate the effectiveness of the proposed decomposition algorithm and its components. The proposed decomposition method is demonstrated on the IEEE 118-bus system.
The success probability of a quantum algorithm constructed from noisy quantum gates cannot be accurately predicted from single-parameter metrics that compare noisy and ideal gates. We illustrate this concept by examining a system with coherent errors and comparing algorithm success rates for different choices of two-qubit gates that are constructed from composite pulse sequences, where the residual gate errors are related by a unitary transformation. As a result, all of the sequences have the same error relative to the ideal gate under any distance measure that is invariant under unitary transformations. However, the circuit success can vary dramatically by choosing error orientations that do not affect the final outcome and error orientations that cancel between conjugate controlled-nots, as demonstrated here with Clifford circuits, compiled Toffoli gates, and quantum simulation algorithms. Furthermore, the results point to the utility of both minimizing the error and optimizing the error direction and also to the advantages of using multiple control sequences for the same gate type within a single algorithm.
Hedrick, E., K. Reynolds, D. Bhattacharyya, S.E. Zitney, and B. Omell, "Development of Algorithms for Reinforcement Learning Augmented Model Predictive Control," AIChE 2021 Annual Meeting, Boston, MA, November 15-19 (2021).
Variational Quantum Algorithms (VQAs) have received considerable attention due to their potential for achieving near-term quantum advantage. However, more work is needed to understand their scalability. One known scaling result for VQAs is barren plateaus, where certain circumstances lead to exponentially vanishing gradients. It is common folklore that problem-inspired ansatzes avoid barren plateaus, but in fact, very little is known about their gradient scaling. In this work we employ tools from quantum optimal control to develop a framework that can diagnose the presence or absence of barren plateaus for problem-inspired ansatzes. Such ansatzes include the Quantum Alternating Operator Ansatz (QAOA), the Hamiltonian Variational Ansatz (HVA), and others. With our framework, we prove that avoiding barren plateaus for these ansatzes is not always guaranteed. Specifically, we show that the gradient scaling of the VQA depends on the degree of controllability of the system, and hence can be diagnosed through the dynamical Lie algebra $\mathfrak{g}$ obtained from the generators of the ansatz. We analyze the existence of barren plateaus in QAOA and HVA ansatzes, and we highlight the role of the input state, as different initial states can lead to the presence or absence of barren plateaus. Taken together, our results provide a framework for trainability-aware ansatz design strategies that do not come at the cost of extra quantum resources. Moreover, we prove no-go results for obtaining ground states with variational ansatzes for controllable system such as spin glasses. Our work establishes a link between the existence of barren plateaus and the scaling of the dimension of $\mathfrak{g}$.
Combating cyberattacks is an emerging challenge in maintaining the reliable and economic operation of electric power systems. Possible cyberattacks include intrusions to the parameter data at a control center. In this class of attacks, algorithms at the control center are correctly executed, but the attacker's modification of the associated parameter data yields improper results. This paper proposes an algorithm for detecting and characterizing cyberattacks to network parameter data, with specific application to optimal power flow problems. The proposed algorithm evaluates whether historical operating point data are consistent with the network parameters. Inconsistencies indicating potential cyberattacks are characterized using historical operational data (power injections and voltage phasors) along with network parameter data. Simulated test cases illustrate the proposed algorithm's detection and characterization capabilities.
To improve the marketability of novel microreactor designs, there is a need for automated and optimal control of these reactors. This paper presents a methodology for performing multiobjective optimization of control drum operation for a microreactor under normal and off-nominal conditions. Here, two different case studies are used where the control drum configuration is optimized for the reactor to be critical with some desired power distribution that would satisfy peaking limits. A surrogate model for power distribution is developed based on a feedforward neural network. The process for determining weights for scalarization of the multiobjective optimization problem is also detailed. Six optimization algorithms: evolutionary strategies, differential evolution, grey wolf optimization, Harris hawks optimization, moth flame optimization and particle swarm optimization, are all applied to these cases and the results analyzed. Although all these algorithms will demonstrate optima-seeking behavior, for real-time control it is necessary to identify the best algorithm to efficiently provide reasonable optima without operator interference. The moth flame optimization algorithm was found to perform particularly well on both cases. Overall, it was found that the algorithms capable of supplying the best optima were also the most consistent. Finally, the found optima were verified with the original model used to train surrogates.
Artificial intelligence technologies have emerged as a game changer not only in specific applications such as image recognition and machine translation but also in many scientific domains. In particular, as deep reinforcement learning (DRL) has shown great success in complex control problems, DRL-based control has been considered as a potential solution to efficiently control and manage building systems. However, broad assessment of DRL-based building control is still required to characterize their pros and cons in comparison with conventional building control methods (e.g., rule-based feedback controls). In this paper, we assessed DRL-based controls with on-policy learning-based algorithms and continuous control actions for cooling control of large office buildings in the summer season to minimize whole-building energy use and occupant discomfort. We compared DRL-based control methods with two baseline control methods: (1) a pre-determined schedule with supply temperature and static pressure setpoints, and (2) advanced reset method that adjusts setpoints based on heuristic rules, i.e., ASHRAE Guideline 36. We also tested the DRL algorithms to evaluate their performances in multiple climate locations. We found that DRL-based control methods outperformed the baseline control methods in terms of energy savings while maintaining a thermal comfort. DRL reduced energy use between ~4%–22% on average compared to the baseline methods, depending on climate location. We also evaluated DRL-based control in terms of control stability and showed that DRL-based methods should address the span of hardware lifetimes in practical operations.
The double-fed induction generator (DFIG) usually experiences high rotor current and DC capacitor link voltage during system fault events. In this paper, a novel data-driven approach is proposed to enhance the DFIG performance under fault scenarios. An advanced reinforcement learning (RL) algorithm called guided surrogate-gradient-based evolution strategy (GSES) is used to control the DFIG power and capacitor DClink voltage by adjusting the optional reference signals. This controller is able to prevent the rotor of DFIG from overcurrent risk and maintain the grid-connected operation. The proposed GSES-based control algorithm was evaluated through simulations on a 3.6-MW DFIG in PSCAD/EMTDC software. Results have validated the effectiveness of the proposed GSESbased control algorithm in improving the DFIG performance under fault scenarios.
Here, this paper presents a refined quantum Harrow Hassidim Lloyd (HHL) algorithm for microgrid control. The first novelty of the developed method is that a mapping shift function enables the original HHL algorithm to handle general linear equations with non-singular and indefinite matrix. Second, a method of Matrix Extension for Amplifying Sampling Probabilities of Intended Solution (ME-ASPI) is proposed to design the reformulated linear algebraic equations, allowing for improved sampling efficiency of the quantum tomography in the refined HHL algorithm. Then, we applied the method to solve the model predictive control (MPC) problem in nonlinear dynamical microgrids. Specifically, with the ME-ASPI method, the refined HHL algorithm can effectively obtain the intended partial optimal control inputs for MPC. The optimization of quadratic programming problem in each time step of MPC is transformed into a linear system problem, which is addressed by the proposed quantum solver through using only partial information, with the time complexity improved from $\mathscr{O}(\mathscr{N}^{2.37286})$ classically to $\mathscr{O}(\mathscr{N}^{2} log \mathscr{N}$ x $p$ log $p)$ in quantum. Numerical examples have validated the effectiveness of the refined HHL algorithm with the proposed mapping function and the ME-ASPI method. By leveraging quantum properties, the proposed method provides a hybrid quantum–classical framework for microgrid control. This generic method can also potentially tackle many other challenges in analyzing and controlling general complex engineered systems.
Online tuning of particle accelerators is necessary in order to achieve optimal machine performance. However, it is also a major challenge due to the large parameter space which must be searched and the fact that many of the desir- able objectives compete with one another, and so will not reach their optimal values simultaneously. In order to mitigate these issues, we have explored using dimension-reduction techniques to reduce the size of the parameter space which must be searched and multi-objective genetic algorithms to obtain the sets of tuning parameters which provide pareto-optimal values for the objectives. These methods have enabled us to obtain improved values of the vertical emittance at the Cornell Electron Storage Ring (CESR), and to do so with greater control of orbit errors. Algorithmic tuning is a multidisciplinary endeavour, requiring expertise in beam dynamics, diagnostics, control systems and computer science, and thus a key practical problem is to formulate a common language in which experts with different specialties can communicate. We developed a solution to this problem in the form of a generic accelerator software interface that allows for rapid prototyping of optimization and control algorithms. Our interface is built on the Experimental Physics and Industrial Control Systems (EPICS) and makes possible testing control code in simulation before deployment on real accelerators, as well as deployment of third-party optimization code.
The ILC algorithm prioritizes available loads for curtailment in large and small/medium size commercial buildings.
This paper presents high precision control and deep learning-based corn stand counting algorithms for a low-cost, ultra-compact 3D printed and autonomous field robot for agricultural operations. Currently, plant traits, such as emergence rate, biomass, vigor, and stand counting, are measured manually. This is highly labor-intensive and prone to errors. The robot, termed TerraSentia, is designed to automate the measurement of plant traits for efficient phenotyping as an alternative to manual measurements. In this paper, we formulate a Nonlinear Moving Horizon Estimator that identifies key terrain parameters using onboard robot sensors and a learning-based Nonlinear Model Predictive Control that ensures high precision path tracking in the presence of unknown wheel-terrain interaction. Moreover, we develop a machine vision algorithm designed to enable an ultra-compact ground robot to count corn stands by driving through the fields autonomously. The algorithm leverages a deep network to detect corn plants in images, and a visual tracking model to re-identify detected objects at different time steps. We collected data from 53 corn plots in various fields for corn plants around 14 days after emergence (stage V3 - V4). The robot predictions have agreed well with the ground truth with C robot =1.02×C human -0.86 and a correlation coefficient R=0.96. The mean relative error given by the algorithm is -3.78%, and the standard deviation is 6.76%. These results indicate a first and significant step towards autonomous robot-based real-time phenotyping using low-cost, ultra-compact ground robots for corn and potentially other crops.
This study aims to develop a concrete occupancy prediction as well as an optimal occupancy-based control solution for improving the efficiency of Heating, Ventilation, and Air-Conditioning (HVAC) systems. Accurate occupancy prediction is a key enabler for demand-based HVAC control so as to ensure HVAC is not run needlessly when when a room/zone is unoccupied. In this paper, we propose simple yet effective algorithms to predict occupancy alongside an algorithm for automatically assigning temperature set-points. Utilizing past occupancy observations, we introduce three different techniques for occupancy prediction. Firstly, we propose an identification-based approach, which identifies the model via Expectation Maximization (EM) algorithm. Secondly, we study a novel finite state automata (FSA) which can be reconstructed by a general systems problem solver (GSPS). Thirdly, we introduce an alternative stochastic model based on uncertain basis functions. The results show that all the proposed occupancy prediction techniques could achieve around 70% accuracy. Then, we have proposed a scheme to adaptively adjust the temperature set-points according to a novel temperature set algorithm with customers’ different discomfort tolerance indexes. By cooperating with the temperature set algorithm, our occupancy-based HVAC control shows 20% energy saving while still maintaining building comfort requirements.
This project evaluated and developed new mathematical and algorithmic techniques capable of handling (in real-time) the growing amounts of data generated by modern fusion research. While existing numerical linear algebra (NLA) methods provide the backbone to classical data analysis and algorithms, these methods fundamentally do not port to distributed architectures nor do they allow low-latency data reduction for control. Motivated by the needs for modern fusion reactors, this project explored and implemented new numerical methods to characterize plasma dynamics, respond in real-time to discharge evolution, and to process massive-scale data accurately and rapidly more fully. This project links expertise in multiple-sensor diagnostics of tokamak plasma dynamics from Columbia University’s Plasma Physics Laboratory with expertise in massive-scale data reduction and extreme data control algorithms at Columbia University’s Data Science Institute. This interdisciplinary project (i) applied machine learning methods, (ii) implemented a properly-trained neural-network for very fast processing of high-speed plasma videography, and (ii) developed the applied mathematical methods, based on randomized-NLA (rNLA) routines, for data analysis, reduction, and real-time control. The Columbia University High Beta Tokamak-Extended Pulse (HBT-EP) facility provided data to test new algorithms and partnership with Columbia University's Data Sciences Institute evaluated the broader use of new algorithms for many challenging control applications.
Transactive energy systems are an alternative solution for the problems that distribution system operators face due to an increase in the use of distributed energy resources(DERs) and resulting much required scalability in managing active distribution system. To meet the reliability, sustainability and security requirement, ecient management and control of DERs including distributed generators, energy storage systems, and demand response is necessary. DERs can provide services such as reactive power compensation, voltage control, energy balancing, peak load reduction. These edge resources can also be used for system restoration after the extreme events within regulatory bound and enabling resiliency of the electric grid. While there are numbers of related work focused on solving these problems, availability of additional data resources has not been utilized to its potential to enable the reliable, sustainable and resilient electric grid. In order to address these challenges, data-driven algorithms have been proposed in this dissertation, including a) Volt/Var control, b) activity aware demand response and c) estimation of behind the meter distributed energy resources. Results indicate satisfactory performance of the developed algorithms.