Optimal continuous review policies for two product inventory systems with joint setup costs
Minimum average cost ordering policies for two product inventory systems with joint setup costs
MANAGEMENT PLANNING↗
SEARCH · Search NASA
Results for “policy 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.
Multi-Agent Safe Policy Learning for Power Management of Networked Microgrids
This paper presents a supervised multi-agent safe policy learning (SMAS-PL) method for optimal power management of networked microgrids (MGs) in distribution systems. While unconstrained reinforcement learning (RL) algorithms are black-box decision models that could fail to satisfy grid operational constraints, our proposed method considers AC power flow equations and other operational limits. Accordingly, the training process employs the gradient information of operational constraints to ensure that the optimal control policy functions generate safe and feasible decisions. Furthermore, we have developed a distributed consensus-based optimization approach to train the agents’ policy functions while maintaining MGs’ privacy and data ownership boundaries. After training, the learned optimal policy functions can be safely used by the MGs to dispatch their local resources, without the need to solve a complex optimization problem from scratch. Lastly, numerical experiments have been devised to verify the performance of the proposed method.
, policy gradient↗
Deep reinforcement learning control of hydraulic fracturing
Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.
42 ENGINEERING↗
An Evolutionary Algorithm to Personalize Stool-Based Colorectal Cancer Screening
Fecal immunochemical testing (FIT) is an established method for colorectal cancer (CRC) screening. Measured FIT-concentrations are associated with both present and future risk of CRC, and may be used for personalized screening. However, evaluation of personalized screening is computationally challenging. In this study, a broadly applicable algorithm is presented to efficiently optimize personalized screening policies that prescribe screening intervals and FIT-cutoffs, based on age and FIT-history. We present a mathematical framework for personalized screening policies and a bi-objective evolutionary algorithm that identifies policies with minimal costs and maximal health benefits. The algorithm is combined with an established microsimulation model (MISCAN-Colon), to accurately estimate the costs and benefits of generated policies, without restrictive Markov assumptions. The performance of the algorithm is demonstrated in three experiments. In Experiment 1, a relatively small benchmark problem, the optimal policies were known. The algorithm approached the maximum feasible benefits with a relative difference of 0.007%. Experiment 2 optimized both intervals and cutoffs, Experiment 3 optimized cutoffs only. Optimal policies in both experiments are unknown. Compared to policies recently evaluated for the USPSTF, personalized screening increased health benefits up to 14 and 4.3%, for Experiments 2 and 3, respectively, without adding costs. Generated policies have several features concordant with current screening recommendations. The method presented in this paper is flexible and capable of optimizing personalized screening policies evaluated with computationally-intensive but established simulation models. It can be used to inform screening policies for CRC or other diseases. For CRC, more debate is needed on what features a policy needs to exhibit to make it suitable for implementation in practice.
60 APPLIED LIFE SCIENCES↗
An Edge-Cloud Integrated Solution for Buildings Demand Response Using Reinforcement Learning
Buildings, as major energy consumers, can provide great untapped demand response (DR) resources for grid services. However, their participation remains low in real-life. One major impediment for popularizing DR in buildings is the lack of cost-effective automation systems that can be widely adopted. Existing optimization-based smart building control algorithms suffer from high costs on both building-specific modeling and on-demand computing resources. To tackle these issues, this paper proposes a cost-effective edge-cloud integrated solution using reinforcement learning (RL). Beside RL’s ability to solve sequential optimal decision-making problems, its adaptability to easy-to-obtain building models and the off-line learning feature are likely to reduce the controller’s implementation cost. Using a surrogate building model learned automatically from building operation data, an RL agent learns an optimal control policy on cloud infrastructure, and the policy is then distributed to edge devices for execution. Simulation results demonstrate the control efficacy and the learning efficiency in buildings of different sizes. A preliminary cost analysis on a 4-zone commercial building shows the annual cost for optimal policy training is only 2.25% of the DR incentive received. Results of this study show a possible approach with higher return on investment for buildings to participate in DR programs.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Optimal design and use of retry in fault tolerant real-time computer systems
A new method to determin an optimal retry policy and for use in retry of fault characterization is presented. An optimal retry policy for a given fault characteristic, which determines the maximum allowable retry durations to minimize the total task completion time was derived. The combined fault characterization and retry decision, in which the characteristics of fault are estimated simultaneously with the determination of the optimal retry policy were carried out. Two solution approaches were developed, one based on the point estimation and the other on the Bayes sequential decision. The maximum likelihood estimators are used for the first approach, and the backward induction for testing hypotheses in the second approach. Numerical examples in which all the durations associated with faults have monotone hazard functions, e.g., exponential, Weibull and gamma distributions are presented. These are standard distributions commonly used for modeling analysis and faults.
Lee, Y. H.↗
Statistical methodologies for the control of dynamic remapping
Following an initial mapping of a problem onto a multiprocessor machine or computer network, system performance often deteriorates with time. In order to maintain high performance, it may be necessary to remap the problem. The decision to remap must take into account measurements of performance deterioration, the cost of remapping, and the estimated benefits achieved by remapping. We examine the tradeoff between the costs and the benefits of remapping two qualitatively different kinds of problems. One problem assumes that performance deteriorates gradually, the other assumes that performance deteriorates suddenly. We consider a variety of policies for governing when to remap. In order to evaluate these policies, statistical models of problem behaviors are developed. Simulation results are presented which compare simple policies with computationally expensive optimal decision policies; these results demonstrate that for each problem type, the proposed simple policies are effective and robust.
Saltz, J. H.↗
Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control
This paper develops an intelligent grid-interactive building controller, which optimizes building operation during both normal hours and demand response (DR) events. To avoid costly on-demand computation and to adapt to non-linear building models, the controller utilizes reinforcement learning (RL) and makes real-time decisions based on a near-optimal control policy. Learning such a policy typically amounts to solving a hard non-convex optimization problem. We propose to address this problem with a novel global-local policy search method. In the first stage, an RL algorithm based on zero-order gradient estimation is leveraged to search for the optimal policy globally, due to its scalability and the potential to escape some poor performing local optima. The obtained policy is then fine-tuned locally to bring the first-stage solution closer to that of the original unsmoothed problem. Experiments on a simulated five-zone commercial building demonstrate the advantages of the proposed method over existing learning approaches. They also show that the learned control policy outperforms a pragmatic linear model predictive controller (MPC) and approaches the performance of an oracle MPC in testing scenarios. Using a state-of-the-art advanced computing system, we demonstrate that the controller can be learned and deployed within hours of training.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Improved microgrid resiliency through distributionally robust optimization under a policy-mode framework
Critical energy infrastructure are constantly under stress due to the ever increasing disruptions caused by wildfires, hurricanes, other weather related extreme events and cyber-attacks. Hence it becomes important to make critical infrastructure resilient to threats from such cyber-physical events. However, such events are hard to predict and numerous in nature and type and it becomes infeasible to make a system resilient to every possible such cyber-physical event. Such an approach can make the system operation overly conservative and impractical to operate. Furthermore, distributions of such events are hard to predict and historical data available on such events can be very sparse, making the problem even harder to solve. To deal with these issues, in this paper we present a policy-mode framework that enumerates and predicts the probability of various cyber-physical events and then a distributionally robust optimization (DRO) formulation that is robust to the sparsity of the available historical data. The proposed algorithm is illustrated on an islanded microgrid example: a modified IEEE 123-node feeder with distributed energy resources (DERs) and energy storage. Simulations are carried to validate the resiliency metrics under the sampled disruption events.
Nazir, Mohammad Nawaf↗
On the determination of optimal costly measurement strategies for linear stochastic systems.
This paper presents the formulation of a class of optimization problems dealing with selecting, at each instant of time, one measurement provided by one out of many sensors. Each measurement has an associated measurement cost. The basic problem is then to select an optimal measurement policy, during a specified observation time interval, so that a weighted combination of prediction accuracy and accumulated observation cost is optimized. The current analysis is limited to the class of linear stochastic dynamic systems and measurement subsystems. The problem of selecting the optimal measurement strategy can be transformed into a deterministic optimal control problem. It is shown that the optimal measurement policy and the associated matched Kalman-type filter can be precomputed.
Athans, M.↗
A Decision-Theoretic Approach to Autonomous Planetary Rover Control
The report discusses the: Decentralized Control of Markov Decision Processes. Study the complexity of decentralized control of Markov decision processes, and develop algorithms for finding optimal control policies. Scheduling Contract Algorithms. Develop an optimal method for scheduling runs of a contract anytime algorithm (one that takes the deadline as input) in situations where the deadline is unknown, multiple problem instances must be solved, and a multi-processor machine is available. Planetary Rover Control as a Markov Decision Process.Use the Markov decision process framework to formalize and solve problems in planetary rover control. Adaptive Peer Selection. Use reinforcement learning to maximize the expected down-load speed for a client in a peer-to-peer file sharing system.
Zilberstein, Shlomo↗
Optimizing equity in energy policy interventions: A quantitative decision-support framework for energy justice
This paper presents a quantitative framework to support policy decision-making around equitable energy interventions. By combining sociodemographic and techno-economic models in the energy space, we propose a linear programming model to calculate the optimal portfolio of energy investments that explicitly minimizes the energy burden of a given population of energy insecure households. The model is formulated as a multi-objective optimization suitable to support the decisions on weatherization and deployment of distributed energy resources. We illustrate our methodology with a case study involving a population of 14,043 energy insecure households in Wayne County, Detroit, United States.
29 ENERGY PLANNING, POLICY, AND ECONOMY↗
Next-Cycle Optimal Fuel Control for Cycle-to-Cycle Variability Reduction in EGR-Diluted Combustion
In this simulation study, cycle-to-cycle fuel control was used to reduce CCV by injecting additional fuel in operating conditions with sporadic misfires and partial burns. An optimal control policy was proposed that utilizes 1) a physics-based model that tracks in-cylinder gas composition and 2) a one-step-ahead prediction of the combustion efficiency based on a kernel density estimator. The optimal solution, however, presents a tradeoff between the reduction in combustion CCV and the increase in fuel injection quantity required to stabilize the charge. Such a tradeoff can be ad- just by a single parameter embedded in the cost function.
Maldonado, BryanP. [Oak Ridge National Lab. (ORNL)↗
Dynamic remapping of parallel computations with varying resource demands
A large class of computational problems is characterized by frequent synchronization, and computational requirements which change as a function of time. When such a problem must be solved on a message passing multiprocessor machine, the combination of these characteristics lead to system performance which decreases in time. Performance can be improved with periodic redistribution of computational load; however, redistribution can exact a sometimes large delay cost. We study the issue of deciding when to invoke a global load remapping mechanism. Such a decision policy must effectively weigh the costs of remapping against the performance benefits. We treat this problem by constructing two analytic models which exhibit stochastically decreasing performance. One model is quite tractable; we are able to describe the optimal remapping algorithm, and the optimal decision policy governing when to invoke that algorithm. However, computational complexity prohibits the use of the optimal remapping decision policy. We then study the performance of a general remapping policy on both analytic models. This policy attempts to minimize a statistic W(n) which measures the system degradation (including the cost of remapping) per computation step over a period of n steps. We show that as a function of time, the expected value of W(n) has at most one minimum, and that when this minimum exists it defines the optimal fixed-interval remapping policy. Our decision policy appeals to this result by remapping when it estimates that W(n) is minimized. Our performance data suggests that this policy effectively finds the natural frequency of remapping. We also use the analytic models to express the relationship between performance and remapping cost, number of processors, and the computation's stochastic activity.
Nicol, D. M.↗
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↗
Defender Policy Evaluation and Resource Allocation With MITRE ATT&CK Data and Evaluations.
Abstract not provided.
97 MATHEMATICS AND COMPUTING↗
Operation Optimization using Reinforcement Learning with Integrated Artificial Reasoning Framework
In large and complex systems, operational decision-making requires a systematic analysis with a vast amount of data from both process parameters and component status monitoring. In this paper, we present an integrated artificial reasoning approach for system state transition models that can help operational decision-making with explainable and traceable reasoning. The integrated artificial reasoning framework is a physics-based approach of defining the system structure in a Bayesian network, so we leveraged it in a Markov decision process (MDP) for finding optimal operational solutions. In our proposed framework, the MDP is implemented on a dynamic Bayesian network (DBN), which represents causalities in a system. The multilevel flow modeling was utilized in order to extract these causalities in a more efficient and objective manner. Since multilevel flow modeling is based on the fundamental energy and mass conservation laws, the target system is decomposed into several mass, energy, and information structures, which serve as the basis for a DBN. The MDP consists of the processes of finding a solution for the Bellman equation, which can be derived from the conditional probability equations of the constructed DBN. System operators can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from the component degradation process or random failures. We analyzed a simplified example system to illustrate finding an optimal operational policy with this approach.
99 GENERAL AND MISCELLANEOUS↗
Implications of stop-and-go traffic on training learning-based car-following control
Learning-based car-following control (LCC) of connected and autonomous vehicles (CAVs) is gaining significant attention with the advancement of computing power and data accessibility. While the flexibility and large model capacity of model-free architecture enable LCC to potentially outperform the model-based car-following (CF) model in improving traffic efficiency and mitigating congestion, the generalizability of LCC for traffic conditions different from the training environment/dataset is not well-understood. Herein, this study seeks to explore the impact of stop-and-go traffic in the training dataset on the generalizability of LCC. It uses the characteristics of lead vehicle trajectories to describe stop-and-go traffic, and links the theory of identifiability (i.e., obtaining a unique parameter estimation result using sensor measurements) to the generalizability of behavior cloning (BC) and policy-based deep reinforcement learning (DRL). Correspondingly, the study shows theoretically that: (i) stop-and-go traffic can enable the property of identifiability and enhance the control performance of BC-based LCC in different traffic conditions; (ii) stop-and-go traffic is not necessary for DRL-based LCC to generalize to different traffic conditions; (iii) DRL-based LCC trained with only constant-speed lead vehicle trajectories (not sufficient to ensure identifiability) can be generalized to different traffic conditions; and (iv) stop-and-go traffic increases variance in the training dataset, which improves the convergence of parameter estimation while negatively impacting the convergence of DRL to the optimal control policy. Numerical experiments validate the above findings, illustrating that BC-based LCC entails comprehensive training datasets for generalizing to different traffic conditions, while DRL-based LCC can achieve generalization with simple free-flow traffic training environments. This further suggests DRL as a more promising and cost-effective LCC approach to reduce operational costs, mitigate traffic congestion, and enhance safety and mobility, which can accelerate the deployment and acceptance of CAVs.
33 ADVANCED PROPULSION SYSTEMS↗