Search NASA⌕ Search

SEARCH · Search NASA

Results for “stochastic optimization”

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.

At least 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
NASA NTRS1999

Multi-Parent Clustering Algorithms from Stochastic Grammar Data Models

We introduce a statistical data model and an associated optimization-based clustering algorithm which allows data vectors to belong to zero, one or several "parent" clusters. For each data vector the algorithm makes a discrete decision among these alternatives. Thus, a recursive version of this algorithm would place data clusters in a Directed Acyclic Graph rather than a tree. We test the algorithm with synthetic data generated according to the statistical data model. We also illustrate the algorithm using real data from large-scale gene expression assays.

Mjoisness, Eric↗
DOE OSTI2026

Dynamic Transmission Line Switching Amid Wildfire-Prone Weather Under Decision-Dependent Uncertainty

During dry and windy seasons, environmental conditions significantly increase the risk of wildfires, exposing power grids to disruptions caused by transmission line failures. Wildfire propagation exacerbates grid vulnerability, potentially leading to prolonged power outages. To address this challenge, we propose a multistage optimization model that dynamically adjusts transmission grid topology in response to wildfire propagation, aiming to develop an optimal response policy. By accounting for decision-dependent uncertainty, where line survival probabilities depend on usage, we employ distributionally robust optimization to model uncertainty in line survival distributions. We adapt the stochastic nested decomposition algorithm and derive a deterministic upper bound for its finite convergence. To enhance computational efficiency, we exploit the Lagrangian dual problem structure for a faster generation of Lagrangian cuts. Using realistic data from the California transmission grid, we demonstrate the superior performance of dynamic response policies against two-stage alternatives through a comprehensive case study. In addition, after solving the multistage formulation, we construct easy-to-implement policies that significantly reduce computational burden while maintaining good performance in real-time deployment. History: Accepted by Russell Bent, Area Editor for Network Optimization: Algorithms and Applications. Funding: This work was supported by the U.S. Department of Energy, Office of Electricity [Grant DE-AC02-05CH11231]. The work of R. Jiang was supported in part by the U.S. National Science Foundation, Division of Electrical, Communications and Cyber Systems [Grant ECCS-1845980] and the U.S. Air Force Office of Scientific Research [Grant FA9550-23-1-0323]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2025.1210 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2025.1210 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Estrada-Garcia, Juan-Alberto↗
NASA NTRS1992

Robustness of solutions to a benchmark control problem

The robustness of 10 solutions to a benchmark control design problem presented at the 1990 American Control Conference has been evaluated. The 10 controllers have second-to-eighth-order transfer functions and have been designed using several different methods, including H-infinity optimization, loop-transfer recovery, imaginary-axis shifting, constrained optimization, structured covariance, game theory, and the internal model principle. Stochastic robustness analysis quantifies the controllers' stability and performance robustness with structured uncertainties in up to six system parameters. The analysis provides insights into system response that are not readily derived from other robustness criteria and provides a common ground for judging controllers produced by alternative methods. One important conclusion is that gain and phase margins are not reliable indicators of the probability of instability. Furthermore, parameter variations actually may improve the likelihood of achieving selected performance metrics, as demonstrated by results for the probability of settling-time exceedance.

Stengel, Robert F.↗
NASA NTRS2012

Using Markov Models of Fault Growth Physics and Environmental Stresses to Optimize Control Actions

A generalized Markov chain representation of fault dynamics is presented for the case that available modeling of fault growth physics and future environmental stresses can be represented by two independent stochastic process models. A contrived but representatively challenging example will be presented and analyzed, in which uncertainty in the modeling of fault growth physics is represented by a uniformly distributed dice throwing process, and a discrete random walk is used to represent uncertain modeling of future exogenous loading demands to be placed on the system. A finite horizon dynamic programming algorithm is used to solve for an optimal control policy over a finite time window for the case that stochastic models representing physics of failure and future environmental stresses are known, and the states of both stochastic processes are observable by implemented control routines. The fundamental limitations of optimization performed in the presence of uncertain modeling information are examined by comparing the outcomes obtained from simulations of an optimizing control policy with the outcomes that would be achievable if all modeling uncertainties were removed from the system.

Bole, Brian↗
NASA NTRS2005

Optimal Estimation of Clock Values and Trends from Finite Data

We show how to solve two problems of optimal linear estimation from a finite set of phase data. Clock noise is modeled as a stochastic process with stationary dth increments. The covariance properties of such a process are contained in the generalized autocovariance function (GACV). We set up two principles for optimal estimation: with the help of the GACV, these principles lead to a set of linear equations for the regression coefficients and some auxiliary parameters. The mean square errors of the estimators are easily calculated. The method can be used to check the results of other methods and to find good suboptimal estimators based on a small subset of the available data.

stationary increments↗
DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2013

Risk-Constrained Dynamic Programming for Optimal Mars Entry, Descent, and Landing

A chance-constrained dynamic programming algorithm was developed that is capable of making optimal sequential decisions within a user-specified risk bound. This work handles stochastic uncertainties over multiple stages in the CEMAT (Combined EDL-Mobility Analyses Tool) framework. It was demonstrated by a simulation of Mars entry, descent, and landing (EDL) using real landscape data obtained from the Mars Reconnaissance Orbiter. Although standard dynamic programming (DP) provides a general framework for optimal sequential decisionmaking under uncertainty, it typically achieves risk aversion by imposing an arbitrary penalty on failure states. Such a penalty-based approach cannot explicitly bound the probability of mission failure. A key idea behind the new approach is called risk allocation, which decomposes a joint chance constraint into a set of individual chance constraints and distributes risk over them. The joint chance constraint was reformulated into a constraint on an expectation over a sum of an indicator function, which can be incorporated into the cost function by dualizing the optimization problem. As a result, the chance-constraint optimization problem can be turned into an unconstrained optimization over a Lagrangian, which can be solved efficiently using a standard DP approach.

Ono, Masahiro↗
NASA NTRS1987

Proof of quasi-adaptivity for the m-measurement feedback class of stochastic control policies

Bounds on expected performance are established which show that the m-measurement feedback (mM) policy for nonlinear stochastic control performs as well or better than the open-loop optimal control policy, and thus is quasi-adaptive in the sense of Witenhausen (1966). The chain of performance inequalities indicate a tendency for the mM policy performance to improve with increasing m. It is suggested that the present analytical method, based on the construction of artificial control sequences denoted as utility controls, can be used to establish performance bounds on other well-known policies, avoiding the extensive Monte Carlo simulations necessary in comparing stochastic control policies.

Bayard, David S.↗
DOE OSTI2025

FEDERATED LEARNING ON STOCHASTIC NEURAL NETWORKS

Federated learning is a machine learning paradigm that leverages edge computing on client devices to optimize models while maintaining user privacy by ensuring that local data remain on the device. However, since all data are collected by clients, federated learning is susceptible to latent noise in local datasets. Factors such as limited measurement capabilities or human errors may introduce inaccuracies in client data. To address this challenge, we propose the use of a stochastic neural network as the local model within the federated learning framework. Stochastic neural networks not only facilitate the estimation of the true underlying states of the data but also enable the quantification of latent noise. We refer to our federated learning approach, which incorporates stochastic neural networks as local models, as federated stochastic neural networks. In this work we will present numerical experiments demonstrating the performance and effectiveness of our method, particularly in handling nonindependent and identically distributed data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Stochastic Model Predictive Control With Gaussian Wind Direction Preview for Wake Steering

This article addresses the problem of wake steering control for wind farms that explicitly consider the tradeoff between farm-level power generation and yaw duty cycle under variable and uncertain wind conditions. A novel stochastic model predictive control (MPC) algorithm is presented, which utilizes a stochastic model of the freestream wind field components in a receding horizon framework to compute optimal yaw set points that maximize the expected value of the farm power while constraining the yaw actuation. Different configurations of the algorithm are evaluated using a steady-state wind farm simulator. The proposed stochastic MPC algorithm can plan control actions over a future prediction horizon based on probabilistic estimates of the incoming wind magnitude and direction.

17 WIND ENERGY↗
DOE OSTI2025

A bilevel multistage stochastic self-scheduling model with indivisibilities for trading in the continuous intraday electricity market

In this paper, we study the profit maximization problem of a virtual power plant trading in the continuous intraday electricity market. Our virtual power plant model is compatible with renewable, and thermal assets, covering a range of virtual power plants currently participating in energy markets. We model the trading problem as a bilevel multistage stochastic program. The upper level of the problem accounts for the profit maximization of the virtual power plant with explicit modeling of the technical constraints of the operational status of the thermal power plant including minimum start-up and shut-down times, ramp-up and ramp-down rates, and minimum generation level. The upper level also decides which continuous and indivisible (fill-or-kill) orders are submitted to the market. The lower-level problem accounts for the clearing of the continuous intraday market, i.e., matching of buy and sell orders. Because of the presence of fill-or-kill orders, the lower-level problem is mixed-integer, which prevents its direct conversion to a single-level problem using duality. In order to solve this challenging problem, we develop a convex-hull extended formulation for the lower-level problem, apply duality theory to obtain a single-level stochastic equivalent formulation, and employ McCormick envelopes to turn the problem into a multistage stochastic mixed-integer linear problem, which we solve using the stochastic dual dynamic integer programming algorithm. We conduct numerical experiments and analyze the optimal trading behavior of a virtual power plant trading in an ideal continuous market without arbitrage.

Bilevel multistage stochastic programming problem↗
NASA NTRS1991

A stochastic regulator for integrated communication and control systems. I - Formulation of control law. II - Numerical analysis and simulation

A state feedback control law for integrated communication and control systems (ICCS) is formulated by using the dynamic programming and optimality principle on a finite-time horizon. The control law is derived on the basis of a stochastic model of the plant which is augmented in state space to allow for the effects of randomly varying delays in the feedback loop. A numerical procedure for synthesizing the control parameters is then presented, and the performance of the control law is evaluated by simulating the flight dynamics model of an advanced aircraft. Finally, recommendations for future work are made.

Liou, Luen-Woei↗
NASA NTRS1972

Nonlinear filtering for random signals in statistically unknown noise.

Natural and effective formulation of the filtering problem involved in satellite orbit determination, aircraft navigation, and missile tracking. The problem arises because the environment of the sensor keeps changing from time to time, and it is quite impractical and sometimes impossible to collect the statistical data of the noise incurred in the observation. Computable filtering equations are deduced. The idea of invariant imbedding along with stochastic differential calculus is used to derive differential equations for the optimal estimate.

Loo, J. T.↗
NASA NTRS2022

Analyzing the Efficacy of Flexible Execution, Replanning, and Plan Optimization for a Planetary Lander

Plan execution in unknown environments poses a number of challenges: uncertainty in domain modeling, stochasticity at execution time, and the presence of exogenous events. These challenges motivate an integrated approach to planning and execution that is able to respond intelligently to variation. We examine this problem in the context of the Europa Lander mission concept, and evaluate a planning and execution framework that responds to feedback and task failure using two techniques: flexible execution and replanning with plan optimization. We develop a theoretical framework to estimate gains from these techniques, and we compare these predictions to empirical results generated in simulation. These results indicate that an integrated approach to planning and execution leveraging flexible execution, replanning, and utility maximization shows significant promise for future tightly-constrained space missions that must address significant uncertainty.

Chien, Steve↗
NASA NTRS2021

Analyzing the Efficacy of Flexible Execution, Replanning, and Plan Optimization for a Planetary Lander

Plan execution in unknown environments poses a number of challenges: uncertainty in domain modeling, stochasticity at execution time, and the presence of exogenous events. These challenges motivate an integrated approach to planning and execution that is able to respond intelligently to variation. We examine this problem in the context of the Europa Lander mission concept, and propose a planning and execution framework that responds to feedback and task failure using two techniques: flexible execution and replanning with plan optimization. We develop a theoretical framework to predict the value of each of these techniques, and we compare these predictions to empirical results generated in simulation. We demonstrate that an integrated approach to planning and execution that is grounded in flexible execution, replanning, and utility maximization will be an enabling technology for future tightly-constrained planetary surface missions.

Chien, Steve↗