Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “stochastic distribution control”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Core Design of the Holos-Quad Microreactor

The Holos-Quad micro-reactor concept, developed by HolosGen LLC, is equipped with a 22 MWt (Mega-Watt thermal) core and an integral power conversion system converting the core thermal energy into approximately 10 MWe (Mega-Watt electric). This design can be configured to support a wide range of applications. It is a very innovative high-temperature gas-cooled reactor concept using TRI-structural ISOtropic particle fuel (TRISO) distributed in graphite hexagonal blocks, cooled with helium in a direct Brayton cycle independently executed by four Subcritical Power Modules (SPMs) fitted into a hardened 40-foot container whose dimensions are in compliance with ISO shipping containers requirements. In FY2019 HolosGen LLC was awarded by the Department of Energy Advanced Research Project Agency-Energy (DOE ARPA-E) under the MEITNER funding program. As part of the MEITNER award, the Argonne National Laboratory (ANL) contributed expertise through two specialized teams: The “Design Team” and the “Resource Team”. The Design Team was dedicated to validate feasibility of the Holos-Quad core and to optimize its core design through neutronics analyses. The Resource Team was dedicated to feasibility verification via high-fidelity codes of Holos-Quad thermal-hydraulic, heat transfer, shielding, and structural aspects. This report summarizes the activities conducted by ANL Design Team. A rigorous design approach based on multi-criteria optimization and code-to-code comparison involving stochastic and high-fidelity deterministic solutions was developed and employed at several evolutionary stages of the Holos-Quad design. Several generations of the Holos-Quad core were designed within this project before converging to the current full-scale Gen 2+ design that is detailed in this report. Figure EA-1 illustrates a cross-sectional view of Gen 2+ Holos-Quad core configuration, and Figure EA-2 provides a simplified perspective view of 1-of-4 SPMs. The Holos-Quad uses four thermal-hydraulically independent SPMs locked into stationary positions during power operation, surrounded by BeO reflector and structural component fully comprised within the dimensional constraints represented by traditional ISO containers. One of the benefits of this approach is to enable transportation of each SPM promptly after irradiation in shielded containers. The core is designed to operate for approximately 8 full-power years while the reactivity controls and power conversion system enable load-following operations. The reactivity controls are represented by independent, diversified, and redundant reactivity control systems based on control drums and redundant sets of shutdown rods. The high-fidelity simulation tools were used to assess detailed power and flux distributions of the three-dimensional full-core or quarter-core of the Gen 2+ configuration. Single-physics and multi-physics simulations of the neutronics code PROTEUS and the thermal-hydraulic code System Analysis Module (SAM) were performed to analyze the Holos design configurations with detailed high-fidelity solutions. The design work performed confirmed feasibility of the Holos-Quad concept, provided realistic design description for detailed design of the operational system, and identified several core design improvements to be further considered for future reactor development activities.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Probing the Atomic-Scale Structure of Amorphous Aluminum Oxide Grown by Atomic Layer Deposition

Atomic layer deposition (ALD) is a well-established technique for depositing nanoscale coatings with pristine control of film thickness and composition. The trimethylaluminum (TMA) and water (H 2 O) ALD chemistry is inarguably the most widely used and yet to date, we have little information about the atomic-scale structure of the amorphous aluminum oxide (AlO x ) formed by this chemistry. This lack of understanding hinders our ability to establish process-structure-property relationships and ultimately limits technological advancements employing AlOx made via ALD. In this work, we employ synchrotron high-energy X-ray diffraction (HE-XRD) coupled with pair distribution function (PDF) analysis to characterize the atomic structure of amorphous AlO x ALD coatings. We combine ex situ and in operando HE-XRD measurements on ALD AlO x and fit these experimental data using stochastic structural modeling to reveal variations in the Al-O bond length, Al and O coordination environment, and extent of Al vacancies as a function of growth conditions. In particular, the local atomic structure of ALD AlO x is found to change with the substrate and number of ALD cycles. The observed trends are consistent with the formation of bulk Al 2 O 3 surrounded by an O-rich surface layer. We deconvolute these data to reveal atomic-scale structural information for both the bulk and surface phases. Overall, this work demonstrates the usefulness of HE-XRD and PDF analysis in improving our understanding of the structure of amorphous ALD thin films and provides a pathway to evaluate how process changes impact the structure and properties of ALD films.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Multi-Fidelity Stochastic Economic Dispatch for Operating Low Carbon Power Grids

Grid operators can address the inherently stochastic nature of renewables by solving a two-stage stochastic programming model that minimizes the cost of dispatch decisions while accounting for the complex grid dynamics. It is common to use a sample average approximation to estimate the expectation of the second stage costs in this model. However, the large sample count needed for numerical accuracy makes effective modeling large-scale electric grids computationally intractable. We introduce a control variate multi-fidelity estimator for the second-stage recourse that enables high quality dispatch decisions in real-time with a reduced computational burden. We obtain a hierarchy of model fidelities by linearizing the AC power flow system representation to DC power flow, and by relaxing transmission and voltage network constraints. We evaluate the performance of our proposed method on a synthetic grid with 73 buses against a deterministic baseline with persistence forecast and a high-fidelity reference. Our analysis shows a computational speed-up of 7.62x with a minimal loss in accuracy. The multi-fidelity method is well suited to fidelity combinations that use a simplified network topology in their lower fidelity model and is an attractive option for applications where accurate grid modeling needed on a limited computational budget.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Functional Traits Resolve Mechanisms Governing the Assembly and Distribution of Nitrogen-Cycling Microbial Communities in the Global Ocean

Microorganisms drive much of the marine nitrogen (N) cycle, which jointly controls the primary production in the global ocean. However, our understanding of the microbial communities driving the global ocean N cycle remains fragmented. Focusing on “who is doing what, where, and how?”, this study draws a clear picture describing the global biogeography of marine N-cycling microbial communities by utilizing the Tara Oceans shotgun metagenomes. The marine N-cycling communities are highly variable taxonomically but relatively even at the functional trait level, showing clear functional redundancy properties. The functional traits and taxonomic groups are shaped by the same set of geo-environmental factors, among which, depth is the major factor impacting marine N-cycling communities, differentiating mesopelagic from epipelagic communities. Latitudinal diversity gradients and distance-decay relationships are observed for taxonomic groups, but rarely or weakly for functional traits. The composition of functional traits is strongly deterministic as revealed by null model analysis, while a higher degree of stochasticity is observed for taxonomic composition. Integrating multiple lines of evidence, in addition to drawing a biogeographic picture of marine N-cycling communities, this study also demonstrated an essential microbial ecological theory—determinism governs the assembly of microbial communities performing essential biogeochemical processes; the environment selects functional traits rather than taxonomic groups; functional redundancy underlies stochastic taxonomic community assembly.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Model Predictive Fault-Tolerant Tracking Control for PDF Control Systems With Packet Losses

In this article, a fault-tolerant tracking control strategy is investigated for nonlinear probability density function (PDF) control systems with the actuator fault, uncertainties, unknown disturbance, and random packet losses. The control input signal dropout and measurement signal dropouts are described as the independent Bernoulli distribution. An adaptive fault diagnosis (FD) observer based on the Lyapunov function is given to simultaneously estimate the fault, disturbance, and state with packet losses. Furthermore, different from the traditional robust fault-tolerant control (FTC), a new active fault-tolerant tracking controller is designed based on the model predictive control framework, which has better adaptive fault-tolerant performance. Finally, the validity of the proposed FTC method has been proved by a simulation study of a papermaking process.

42 ENGINEERING↗
DOE OSTI2025

Optimal Control of Differentially Private EV Charging: A Scalable Learning Approach Under Uncertainty

Internet of Things (IoT)-enabled electric vehicles (IoEVs) enable intelligent charging coordination that accounts for grid congestion. However, increased data exchange raises privacy concerns, as charging patterns can reveal sensitive driver behavior to grid operators. Here, we propose a differentially private (DP) EV charging framework that enables coordinated control while protecting driver data with theoretical privacy guarantees. Nevertheless, integrating DP inevitably introduces uncertainty into the control strategy for EVs, which can lead to infeasible solutions. To tackle this challenge, we develop a feasible and scalable control algorithm based on constrained reinforcement learning (CRL) and convex hulls. While our framework is designed to handle the uncertainty introduced by DP, it is general and also applicable to other sources of uncertainty in EV charging, such as the stochastic nature of driver behavior and renewable variability. This ensures feasible and privacy-preserving coordination of EV charging at scale. Our method constructs convex hulls within the action space to guarantee feasibility under stochastic constraints and incorporates constraint reduction techniques to improve scalability. Case studies based on IEEE benchmark systems demonstrate that the proposed approach effectively balances feasibility under uncertainty, scalability, and privacy in large-scale EV charging control.

Engineering - Power transmission and distribution↗
DOE OSTI2020

Efficient Distance-based Global Sensitivity Analysis for Terrestrial Ecosystem Modeling

Sensitivity analysis in terrestrial ecosystem modeling is important for understanding controlling processes, guiding model development, and targeting new observations to reduce parameter and prediction uncertainty. Complex and computationally expensive terrestrial ecosystem models (TEM) limit the number of ensemble simulations, requiring sophisticated and efficient methods to analyze sensitivities of multiple model responses to different types of parameter uncertainties. In this study, we propose a distance-based global sensitivity analysis (DGSA) method. DGSA first classifies model response samples into a small set of discrete classes and then calculates the distance between parameter frequency distributions in different classes to measure the parameter sensitivity. The principle is that, if the parameter distribution is the same in each class, then the model response is insensitive to the parameter, while a large difference in the distributions indicates the parameter is influential to the response. Built on this idea, DGSA can be applied to analyze sensitivity of a single and a group of responses to different kinds of parameter uncertainties including continuous, discrete and even stochastic. Besides the main-effect sensitivity from a single parameter, DGSA can also quantify the sensitivity from parameter interactions. Additionally, DGSA is computationally efficient which can use a small number of model evaluations to obtain an accurate and statistically significant result. We applied DGSA to two TEMs, one having eight parameters and three kinds of model responses, and the other having 47 parameters and a long-period response. We demonstrated that DGSA can be used for sensitivity problems with multiple responses and high-dimensional parameters efficiently.

Lu, Dan↗
DOE OSTI2022

A Q-Learning-Based Approach for Distributed Beam Scheduling in mmWave Networks

We consider the problem of distributed downlink beam scheduling and power allocation for millimeter-Wave (mmWave) cellular networks where multiple base stations (BSs) belonging to different service operators share the same unlicensed spectrum with no centralized control or explicit coordination among them. Our goal is to design efficient distributed beam scheduling and power allocation schemes such that the network-level payoff, defined as the weighted sum of the total throughput and a power penalization term, can be maximized. To this end, we propose a distributed scheduling approach to power allocation and adaptation for efficient interference management over the shared spectrum by modeling each BS as an independent Q-learning agent. As a baseline, we compare the proposed approach to the state-of-the-art non-cooperative game-based approach which was previously developed for the same problem. We conduct extensive experiments under various scenarios to verify the effect of multiple factors on the performance of both approaches. Experiment results show that the proposed approach adapts well to different interference conditions by learning from experience and thus can achieve higher payoff than the game-based approach. The proposed approach can also be integrated into our previously developed Lyapunov stochastic optimization framework for the purpose of network utility maximization with optimality guarantee. As a result, the weights in the payoff function can be automatically and optimally determined by the virtual queue values from the sub-problems derived from the Lyapunov optimization framework.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

High Performance Adaptive Deep-Reinforcement-Learning-based Real-time Emergency Control (HADREC) to Enhance Power Grid Resilience in Stochastic Environment (Final Report)

The HADREC technology developed in this project features real-time, validated, and predictive emergency control capabilities needed to effectively safeguard the grid against costly disturbances from extreme weather and other disruptive events. It has the potential to revolutionize the emergency control by providing faster and more effective solution for power grid emergency control. The technology can reduce the grid emergency control action time from minutes to seconds and mitigate the impact of outages and reduce system recovery time. The evaluation results using the models and data from PacifiCorp system have shown ~20% improvement in responding time and 70% improved in tripped generator output, comparing against today’s industrial application. This performance can help reduce preventive measurements and improve network utilization and market efficiency, and help lead to a more reliable and resilient power grid with renewable integration. The project has generated significant interest from industry, academic and commercial companies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Modern Monte Carlo methods for efficient uncertainty quantification and propagation: A survey

Uncertainty quantification (UQ) includes the characterization, integration, and propagation of uncertainties that result from stochastic variations and a lack of knowledge or data in the natural world. Monte Carlo (MC) method is a sampling-based approach that has widely used for quantification and propagation of uncertainties. However, the standard MC method is often time-consuming if the simulation-based model is computationally intensive. This article gives an overview of modern MC methods to address the existing challenges of the standard MC in the context of UQ. Specifically, multilevel Monte Carlo (MLMC) extending the concept of control variates achieves a significant reduction of the computational cost by performing most evaluations with low accuracy and corresponding low cost, and relatively few evaluations at high accuracy and corresponding high cost. Multifidelity Monte Carlo (MFMC) accelerates the convergence of standard Monte Carlo by generalizing the control variates with different models having varying fidelities and varying computational costs. Multimodel Monte Carlo method (MMMC), having a different setting of MLMC and MFMC, aims to address the issue of UQ and propagation when data for characterizing probability distributions are limited. Multimodel inference combined with importance sampling is proposed for quantifying and efficiently propagating the uncertainties resulting from small data sets. All of these three modern MC methods achieve a significant improvement of computational efficiency for probabilistic UQ, particularly uncertainty propagation. Finally, an algorithm summary and the corresponding code implementation are provided for each of the modern MC methods. The extension and application of these methods are discussed in detail.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Power System Resilience Enhancement in Typhoons Using a Three-Stage Day-Ahead Unit Commitment

In this work, we propose a three-stage resilient unit commitment model which considers uncertain typhoon paths and line outages to improve the power system resilience against typhoon events. The proposed solution coordinates resources in response to the worst-case scenario for each possible typhoon path. The optimal decision is based on the characterization of the power system schedule into three stages of preventive control, emergency control, and restoration. Preventive control is performed before the typhoon occurs by quickly adjusting the three-stage resilient unit commitment schedule; emergency control is conducted during the typhoon by shedding local loads to meet the power balance, while other control strategies are assumed to be unavailable due to possible interruptions in the communication system; restoration is realized after the typhoon, when resources are optimally dispatched to repair the outages of critical devices and recover the normal operation state of the power system quickly. Considering the typhoon path uncertainty, we have introduced a stochastic model for possible typhoon paths where all possible affected lines along each typhoon path are assumed to be on outage during the typhoon. Accordingly, we explore the strategy for co-optimizing the three stages in unit commitment. The proposed model is tested on the IEEE 118-bus system and the real-world provincial system to verify its effectiveness.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Interpretable Data-Driven Probabilistic Power System Load Margin Assessment with Uncertain Renewable Energy and Loads

The increasing uncertainties caused by the high-penetration of stochastic renewable generation resources poses a significant threat to the power system voltage stability. To address this issue, this paper proposes a probabilistic deep kernel learning enabled surrogate model to extract the hidden relationship between uncertain sources, i.e., wind power and loads, and load margin for probabilistic load margin assessment (PLMA). Unlike other deep learning approaches, a kernel SHAP provides the sensitivity analysis as well as interpretability of the inputs to outputs influences. This allows identifying the critical factors that affect load margin so that corrective control can be initiated for stability enhancement. Numerical results carried out on the IEEE 118-bus power system demonstrate the accuracy and efficiency of the proposed data-driven PLMA scheme.

deep kernel learning↗
DOE OSTI2022

Volt-VAR Optimization in Distribution Networks Using Twin Delayed Deep Reinforcement Learning

Modern distribution grids are undergoing new challenges due to the stochastic nature of distributed energy resources (DERs). High penetration of DERs has a significant impact on Volt-VAR profile and system power losses. This work proposes a deep reinforcement learning (DRL)-based Volt-VAR optimization approach for improving voltage profile and reducing system power loss under high penetration of distributed energy resources, such as battery energy storage and solar photovoltaic units in distribution grids. The twin delayed deep deterministic policy gradient (TD3) method-based DRL agent is proposed to configure optimal set-points of reactive power outputs of fast responding smart inverters. The agent schedules the reactive power of inverters according to their physical capabilities, such as minimum allowed power factor, e.g., 0.9 leading/lagging. The reward function of the proposed DRL scheme is designed carefully to ensure a proper voltage profile of the grids with effective scheduling of reactive power outputs from inverters. The performance of the proposed model is verified on modified IEEE 34- and 123-bus systems and compared with base case with no reactive supply by inverters, and local droop Volt-VAR control approach. The results show that the proposed method performs better than the local droop control and deep deterministic policy gradient (DDPG)-based DRL method for reducing voltage fluctuation and minimizing power loss.

Hossain, Rakib↗
DOE OSTI2022

Radio AGN in nearby dwarf galaxies: the important role of AGN in dwarf galaxy evolution

ABSTRACT We combine deep optical and radio data, from the Hyper Suprime-Cam and the Low-Frequency Array (LOFAR), respectively, to study 78 radio active galactic nuclei (AGN) in nearby (z < 0.5) dwarf galaxies. Comparison to a control sample, matched in stellar mass and redshift, indicates that the AGN and controls reside in similar environments, show similar star formation rates (which trace gas availability) and exhibit a comparable incidence of tidal features (which indicate recent interactions). We explore the AGN properties by combining the predicted gas conditions in dwarfs from a cosmological hydrodynamical simulation with a Monte Carlo suite of simulated radio sources, based on a semi-analytical model for radio-galaxy evolution. In the subset of LOFAR-detectable simulated sources, which have a similar distribution of radio luminosities as our observed AGN, the median jet powers, ages, and accretion rates are ∼1035 W, ∼5 Myr, and ∼10−3.4 M⊙ yr−1, respectively. The median mechanical energy output of these sources is ∼100 times larger than the median binding energy expected in dwarf gas reservoirs, making AGN feedback plausible. Since special circumstances (in terms of environment, gas availability, and interactions) are not necessary for the presence of AGN, and the central gas masses are predicted to be an order of magnitude larger than that required to fuel the AGN, AGN triggering in dwarfs is likely to be stochastic and a common phenomenon. Together with the plausibility of energetic feedback, this suggests that AGN could be important drivers of dwarf galaxy evolution, as is the case in massive galaxies.

Davis, F. (ORCID:0000000285224980)↗
DOE OSTI2021

Per-Phase and 3-Phase Optimal Coordination of Directional Overcurrent Relays Using Genetic Algorithm

Penetration of the power grid by renewable energy sources, distributed storage, and distributed generators is becoming increasingly common. Increased utilization of these distributed energy resources (DERs) has given rise to additional protection coordination concerns, particularly where they are utilized in an unbalanced manner or where loading among phases is unbalanced. Digital relays such as the SEL-751 (produced by Schweitzer Engineering Laboratories, Pullman, WA, USA) series have the capability of being set on a per-phase basis. This capability is underutilized in common practice. Additionally, in optimization algorithms for determining relay settings, the time-overcurrent characteristics (TOCs) of relays are generally not treated as variables and are assigned before running the optimization algorithm. In this paper, TOC options themselves are treated as discrete variables to be considered in the optimization algorithm. A mixed integer nonlinear programming problem (MINLP) is set up where the goal is to minimize relay operating times. A genetic algorithm (GA) approach is implemented in MATLAB where two cases are considered. In the first case, the TOC and Time dial setting (TDS) of each relay is set on a three-phase basis. In the second case, per-phase settings are considered. Relay TDSs and TOCs are both considered as simultaneous discrete control variables. Despite the stochastic nature of using per-phase settings for unbalanced systems is found to generally allow for shorter operating times. However, for relatively balanced systems, it is best to use three-phase settings if computation time is of importance.

Matthews, Ronald C.↗
DOE OSTI2020

NREL CITIES Support (CRADA CRD-14-00558 Final Report)

The Technical University of Denmark has received a Grant from the Danish Council for Strategic Research for the project "CITIES - Centre for IT-Intelligent Energy Systems in Cities", a strategic research centre, which involves industrial partners and universities. The Alliance for Sustainable Energy, LLC will participate with DTU as an industrial partner in "CITIES" under this Cooperative Research and Development Agreement (CRADA). The Centre for IT based Intelligent Energy Systems in Cities (CITIES) Project is a Danish national research center focused on work in building short-term operational integrated energy system models that feed longer term plam1ing models, considering the spatio-temporal variations, interactions, dynamics and stochastics in the energy system, from production to consumption. CITIES will harness the extensive expertise and experience of its industrial and academic partners to conduct meaningful research with tangible outputs, including a roadmap to a fossil free future. Decision support tools will be developed to inform stakeholders of the impact of investment, control and policy measures and to identify further opportunities for energy system efficiency. Dissemination and transferring knowledge is a key value to this CRADA, and the use of results by Danish policymakers, industry and society is vital. All participants in the Centre for IT based Intelligent Energy Systems in Cities (CITIES) Project are therefore encouraged to use all means to communicate their findings to society. Wherever possible, and compatible with applicable intellectual property regulations, publications should be produced and disseminated under Open Science, Data, Source and Access principles.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Dynamics Informed Optimization for Resilient Energy Systems

Optimal mitigation planning for highly disruptive contingencies to a transmission-level power system requires optimization with dynamic power system constraints, due to the key role of dynamics in system stability to major perturbations. We formulate a generalized disjunctive program to determine optimal grid component hardening choices for protecting against major failures, with differential algebraic constraints representing system dynamics (specifically, differential equations representing generator and load behavior and algebraic equations representing instantaneous power balance over the transmission system). We optionally allow stochastic optimal pre-positioning across all considered failure scenarios, and optimal emergency control within each scenario. This novel formulation allows, for the first time, analyzing the resilience interdependencies of mitigation planning, preventive control, and emergency control. Using all three strategies in concert is particularly effective at maintaining robust power system operation under severe contingencies, as we demonstrate on the Western System Coordinating Council (WSCC) 9-bus test system using synthetic multi-device outage scenarios. Towards integrating our modeling framework with real threats and more realistic power systems, we explore applying hybrid dynamics to power systems. Our work is applied to basic RL circuits with the ultimate goal of using the methodology to model protective tripping schemes in the grid. Finally, we survey mitigation techniques for HEMP threats and describe a GIS application developed to create threat scenarios in a grid with geographic detail.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

How good are learning-based control v.s. model-based control for load shifting? Investigations on a single zone building energy system

Both model predictive control (MPC) and deep reinforcement learning control (DRL) have been presented as a way to approximate the true optimality of a dynamic programming problem, and these two have shown significant operational cost saving potentials for building energy systems. Furthermore, there is still a lack of in-depth quantitative studies on their approximation levels to the true optimality, especially in the building energy domain. To fill in the gap, this paper provides a numerical framework that enables the evaluation of the optimality levels of different controllers for building energy systems. This framework is then used to comprehensively compare the optimal control performance of both MPC and DRL controllers with given computation budgets for a single zone fan coil unit system. Note the optimality is estimated based on a user-specific selection of trade-off weights among energy costs, thermal comfort and control slew rates. Compared with the best optimality we can find through expensive optimization simulations, the best DRL agent can maximally approximate the optimality by 96.54%, which outperforms the best MPC whose optimality level is 90.11%. However, due to the stochasticity, the DRL agent is only expected to approximate the optimality by 90.42%, which is almost equivalent to the best MPC. Except for Proximal Policy Optimization (PPO), all DRL agents can have a better approximation to the optimality than the best MPC, and are expected to have better approximation than the MPC with a prediction horizon of 32 steps (15 min per step). In terms of reducing energy cost and thermal discomfort, MPC can outperform the rule-based control (RBC) by 18.47%–25.44%. DRL can be expected to outperform RBC by 18.95%–25.65% ,and the best DRL control policy can outperform RBC by 20.29%–29.72%. Although the comparison of the optimality level is performed in a perfect setting, e.g., MPC assumes perfect models, and DRL assumes a perfect offline training process and online deployment process, this can shed insight on their capabilities of approximating to the original dynamic programming problem.

24 POWER TRANSMISSION AND DISTRIBUTION↗