SEARCH · Engineering Papers

Results for “Gradient-based 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

149 records · Page 9

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Approximate Dynamic Programming With Enhanced Off-Policy Learning for Coordinating Distributed Energy Resources

Herein this paper proposes an innovative approximate dynamic programming (ADP) method for distributed energy resource coordination with the loss of life of battery energy storage system (BESS) explicitly modeled. The dispatch policy is designed to account for both calendrical and cyclical aging effects on BESS, explicitly modeling the impacts of ambient temperature on BESS lifespan. The proposed ADP employs an adaptive critic method and enhanced off-policy deterministic policy gradient (DPG) strategy, addressing the limitations of the on-policy gradient-based ADP approaches, including inadequate exploration, low data usage, and computational complexity. In particular, a customized policy is proposed to guide the algorithm to explore some promising decisions and thereby improve exploration capability and learning efficiency compared to conventional DPG-based learning approaches, which may struggle to find a global optimum due to random noisy action-based exploration or require expert demonstration with extra effort. The proposed method is illustrated using the IEEE 123-node system and compared with the existing ADP methods to prove solution accuracy and demonstrate the effects of incorporating degradation models into control design. Case studies showed that the proposed ADP effectively coordinates DERs with a 10 times smaller optimization gap compared to existing methods, and the incorporation of the BESS life loss model ensures the expected lifespan and results in significant cost savings.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2020

Multimodal Data Fusion via Entropy Minimization

The use of gradient-based data-driven models to solve a range of real-world remote sensing problems can in practice be limited by the uniformity of available data. Use of data from disparate sensor types, resolutions, and qualities typically requires compromises based on assumptions that are made prior to model training and may not necessarily be optimal given over-arching objectives. For example, while deep neural networks (NNs) are state-of-the-art in a variety of target detection problems, training them typically requires either limiting the training data to a subset over which uniformity can be enforced or training independent models which subsequently require additional score fusion. The method we introduce here seeks to leverage the benefits of both approaches by allowing correlated inputs from different data sources to co-influence preferred model solutions, while maintaining flexibility over missing and mismatching data. In this work we propose a new data fusion technique for gradient updated models based on entropy minimization and experimentally validate it on a hyperspectral target detection dataset. We demonstrate superior performance compared to currently available techniques using a range of realistic data scenarios, where available data has limited spacial overlap and resolution.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Nonlinear Matrix Approximation with Radial Basis Function Components

We introduce and investigate matrix approximation by decomposition into a sum of radial basis function (RBF) components. An RBF component is a generalization of the outer product between a pair of vectors, where an RBF function replaces the scalar multiplication between individual vector elements. Even though the RBF functions are positive definite, the summation across components is not restricted to convex combinations and allows us to compute the decomposition for any real matrix that is not necessarily symmetric or positive definite. We formulate the problem of seeking such a decomposition as an optimization problem with a nonlinear and non-convex loss function. Several modern versions of the gradient descent method, including their scalable stochastic counterparts, are used to solve this problem. We provide extensive empirical evidence of the effectiveness of the RBF decomposition and that of the gradient-based fitting algorithm. While being conceptually motivated by singular value decomposition (SVD), our proposed nonlinear counterpart outperforms SVD by drastically reducing the memory required to approximate a data matrix with the same L2 error for a wide range of matrix types. For example, it leads to 2 to 6 times memory save for Gaussian noise, graph adjacency matrices, and kernel matrices. Moreover, this proximity-based decomposition can offer additional interpretability in applications that involve, e.g., capturing the inner low-dimensional structure of the data, retaining graph connectivity structure, and preserving the acutance of images.

Rebrova, Elizaveta↗

DOE OSTI2020

Remote Radiation Sensing Using Aerial and Ground Platforms

Remote sensing of ionizing radiation has a significant role in waste management, nuclear material management and nonproliferation, and radiation safety. Robotic platforms can surpass the number of tasks that are achieved by humans. With this technique, the operator's radiation exposure can be decreased. Remote sensing allows for the evaluation and monitoring of radiological contamination. Gamma-ray and neutron sensors were integrated onto the robotic platforms. This approach allows for the radiation sensor data to be dynamically tracked and mapped thus enabling further analysis of the radiation flux in temporal and spatial domains. The goal is to complete scheduled tasks while the robot is being irradiated. To achieve this, electronic components must be shielded and radiation hardened. CZT Detector: Cadmium Zinc Telluride (CZT) detector technology has been a promising solution for gamma-ray and x-ray measurements. Detector data is transferred to the Odroid minicomputer that controls and powers the module via the USB. Robot Operating System (ROS) was utilized for data acquisition and data fusion. The Mariscotti method was employed for the spectrum analysis. A function was programmed in ROS for the automatic identification of photopeaks. CLYC Detector: A Cs{sub 2}LiYCl{sub 6}:Ce{sup 3+} (CLYC) detector was used for simultaneous medium-resolution gamma-ray measurements and neutron counting. A 2.54 cm diameter photomultiplier tube (PMT) was equipped with a high voltage supply and a miniature digitizer. Gamma-ray excitation: fast core-to-valence luminescence (CVL) with 1 ns decay constant, and prompt Ce{sup 3+} emission with 50 ns decay constant. Neutron excitation: slow cerium self-trapped excitation (Ce{sup 3+} STE), 1000 ns decay constant. Radiation Source Localization: Maximum Likelihood Estimation (MLE) and gradient-based methods were used to locate the position of a radiation source based on measured radiation intensities. Multi-Particle Transport Code FLUKA: Estimation of radiation damage of the electronic components is important in order to optimize the robot's operational time while it is irradiated. Displacement per atom (DPA) represents the radiation damage in materials exposed to the ionizing radiation. Various shielding layers of different thickness t were analyzed (< 5% statistical error). The model of the controller of the UAS was designed in FLUKA. Conclusion: CZT and CLYC detectors were integrated onto the robotic platforms. Radiation source localization and contour mapping using robotic platforms were studied. Functions for data analysis and fusion were developed in ROS. FLUKA code was utilized to analyze DPA values. Layers of low-density and high-density materials were used to shield the UAS electronics.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2024

Learning with Adaptive Conservativeness for Distributionally Robust Optimization: Incentive Design for Voltage Regulation: Preprint

Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple iterations. We introduce a model-based online learning algorithm for the DSO, aimed at inferring the relationship between incentives and DERA responses. Given the uncertain nature of these responses, we also propose a distributionally robust incentive design model to control the probability of voltage regulation failure and then reformulate it into a convex problem. This model allows the DSO to periodically revise distribution assumptions on uncertain parameters in the decision model of the DERA. Finally, we present a gradient-based method that permits the DSO to adaptively modify its conservativeness level, measured by the size of a Wasserstein metric-based ambiguity set, according to historical voltage regulation performance. The effectiveness of our proposed method is demonstrated through numerical experiments.

distribution system operator↗