Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning 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 1,225 records · Page 68

First Ever Polymer Flood Field Pilot to Enhance the Recovery of Heavy Oils on Alaska North Slope – Producer Responses and Operational Lessons Learned

The US Department of Energy and Hilcorp Alaska, LLC are jointly cosponsoring a field pilot project entitled “First Ever Field Pilot on Alaska’s North Slope to Validate the Use of Polymer Floods for Heavy Oil Enhanced Oil Recovery (EOR).” The objective of this pilot is to perform a field experiment to validate the use of an advanced polymer flooding technology to unlock the vast heavy oil resources on Alaska North Slope (ANS). Two pairs of horizontal injection and production wells have been deployed in an isolated fault block of the Schrader Bluff heavy oil reservoir at the Milne Point Field to conduct a polymer flood pilot which was designed to acquire field performance data to optimize polymer flood design in the Schrader Bluff heavy oil reservoirs on ANS. Hydrolyzed polyacrylamide (HPAM) polymer injection started on August 28, 2018 using a custom made polymer mixing and pumping unit. Polymer solution properties such as concentration, viscosity, and filter ratio, have been closely monitored and adjusted as necessary. Operational procedures have been improved to ensure adequate injectivity and polymer propagation through the formation. Oil and water production is tested frequently to monitor water cut performance, and produced water is sampled and analyzed for polymer content. Tracers were pumped pre and post polymer injection startup to compare polymer flood breakthrough timing and sweep efficiency. Polymer injectivity of the horizontal wells drilled in the Schrader Bluff NB sand is found to be sufficient to replace the reservoir production voidage although there were some declines as high viscosity polymer swept the near wellbore region. Production data show significant reduction in water cut and the oil production rate has stabilized. No polymer production has been confirmed from the two horizontal producers after 22 months of polymer injection into the two supporting horizontal injectors. Tracer data show very low sweep efficiencies with waterflood alone, whereas significant improvement has been achieved with polymer flood. Many operational lessons have been learned and improvements have been made regarding polymer mixing, pumping, and onsite quality control, particularly in a challenging Arctic environment. Adequate polymer injection rate can be achieved with diligent monitoring and quality assurance of the properties of the injected polymer solution.

Ning, Samson↗

Extending The Realm of Optimization for Complex Systems: Uncertainty, Competition, And Dynamics

Research reported addressed these topics: the development of analytical and algorithmic tools for distributed computation of Nash equilibria; synchronization in mean-field oscillator games, with an emphasis on learning and efficiency analysis; questions that combine learning and computation; questions including stochastic and mean-field games; modeling and control in the context of power markets.

97 MATHEMATICS AND COMPUTING↗

Progress of Gas Injection EOR Surveillance in the Bakken Unconventional Play—Technical Review and Machine Learning Study

Although considerable laboratory and modeling activities were performed to investigate the enhanced oil recovery (EOR) mechanisms and potential in unconventional reservoirs, only limited research has been reported to investigate actual EOR implementations and their surveillance in fields. Eleven EOR pilot tests that used CO2, rich gas, surfactant, water, etc., have been conducted in the Bakken unconventional play since 2008. Gas injection was involved in eight of these pilots with huff ‘n’ puff, flooding, and injectivity operations. Surveillance data, including daily production/injection rates, bottomhole injection pressure, gas composition, well logs, and tracer testing, were collected from these tests to generate time-series plots or analytics that can inform operators of downhole conditions. A technical review showed that pressure buildup, conformance issues, and timely gas breakthrough detection were some of the main challenges because of the interconnected fractures between injection and offset wells. The latest operation of co-injecting gas, water, and surfactant through the same injection well showed that these challenges could be mitigated by careful EOR design and continuous reservoir monitoring. Reservoir simulation and machine learning were then conducted for operators to rapidly predict EOR performance and take control actions to improve EOR outcomes in unconventional reservoirs.

Energy & Fuels↗

Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac

Machine learning (ML) has the potential for significant impact on the modeling, operation, and control of particle accelerators due to its ability to model nonlinear behavior, interpolate on complicated surfaces, and adapt to system changes over time. Anomaly detection in particular has been highlighted as an area where ML can significantly impact the operation of accelerators. These algorithms work by identifying subtle behaviors of key variables prior to negative events. Efforts to apply ML to anomaly detection have largely focused on subsystems such as RF cavities, superconducting magnets, and losses in rings. However, dedicated efforts to understand how to apply ML for anomaly detection in linear accelerators have been limited. In this paper the use of autoencoders is explored to identify anomalous behavior in measured data from the Fermilab low-energy linear accelerator.

Edelen, Jonathan P. (ORCID:0000000215180652)↗

Droplet Entrainment in Steam Supply System of Water-Cooled Small Modular Reactors: Experiment and Modeling Approaches

Droplet entrainment in steam-flow is a prominent phenomenon that needs adequate safety and risk analysis of postulated transient and accident scenarios—including experimental investigation and representative modeling and simulation (M&S)—for small modular reactor (SMR) system design and demonstration. This study identifies knowledge gaps by evaluating experimental and computational fluid dynamics modeling approaches to support early-stage reactor system design, testing, and model evaluation. Previous studies reported in the literature for steam-flow entrainment primarily focused on gigawatt capacity pressurized water reactor (PWR) systems. However, entrainment phenomena are even more prominent for PWR-type SMRs due to their more compact integrated designs, which need further research and development. To fill the research gaps, this study provides insight by specifying the phenomena of interest by leveraging the lessons learned from past research, adopting advanced M&S techniques and advanced instrumentation and control. The findings and recommendations are applicable for evaluating steam-flow entrainment models and for designing integral effect test and separate effect test facilities for gaining reactor design approvals.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

A Systematic Framework for Tuning Open-Source Multifunctional IBR Models To Emulate OEM Black-Box Fault Dynamics

This paper presents a systematic framework to tune a generic IBR EMT model to match with an OEM provided balckbox inverter model based on the fault current responses. The key learnings and findings are summarized as follows: The tunable key parameters include inner control loops and current limiters to align the fault current magnitude, sequence content, and phase trajectories with the OEM models across diverse fault type and locations. The tuned model's fidelity is validated through comparative analysis with an OEM blackbox model, assessing both the fault current response and the responses of multiple relay elements. The results demonstrate the tuned generic model can trigger relay decision logic that is identical or near identical to that of the OEM model, thus generating very good match model for fault studies.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Secret Objective Standoff: International Safeguards Educational Exercise

The International Safeguards Regime, being so multi-faceted, can be overwhelming to those first introduced to its many components. The organizers and lecturers of workshops and courses on nonproliferation often provide a series of independent lectures and must somehow demonstrate the cohesive and effective nature of the system. An exercise titled The Secret Objective Standoff was developed to complement lectures with hands-on learning to assist participants in bringing all the many components (IAEA agreements, export controls, treaty obligations, international diplomacy, etc.) of the International Safeguards Regime together. This exercise divides participants into teams that are assigned the role of either a country or the IAEA and asks that they fully immerse themselves in their roles. The teams are then randomly assigned three unique and secret objectives that are intended to represent realistic and current geopolitical scenarios. Through construction, trading, or hoarding of four resources (experts, technology, money, and uranium), the teams have a finite number of turns to accomplish their objectives. Each turn has three phases random dispersal of resources, a timed discussion where teams can coordinate and strategize with others, and an action phase. During the action phase, teams inform the moderator individually and secretly what they will be doing that turn. The exercise has been tested twice with Oak Ridge National Laboratory personnel, and has been conducted with outside participants twice, in each case the experience was well received by both participants and instructors. This exercise provides instructors the ability to modify the exercise before or during game play to best fit their educational goals. By offering a range of experiences, from an in-depth look at specific components to a generalized overview, this exercise is an effective tool in helping participants achieve a full understanding the International Safeguards Regime.

Okowita, Samantha L↗

New York Marcellus Shale: Industry boom put on hold

Key catalysts for Marcellus Shale drilling in New York were identified. New York remains the only state in the nation with a legislative moratorium on high-volume hydraulic fracturing, as regulators and state lawmakers work to balance the advantages of potential economic benefits while protecting public drinking water resources and the environment. New York is being particularly careful to work on implementing sufficiently strict regulations to mitigate the environmental impacts Pennsylvania has already seen, such as methane gas releases, fracturing fluid releases, flowback water and brine controls, and total dissolved solids discharges. In addition to economic and environmental lessons learned, the New York Department of Environmental Conservation (DEC) also acknowledges impacts to housing markets, security, and other local issues, and may impose stringent measures to mitigate potential risks to local communities. Despite the moratorium, New York has the opportunity to take advantage of increased capital investment, tax revenue generation, and job creation opportunities by increasing shale gas activity. The combination of economic benefits, industry pressure, and recent technological advances will drive the pursuit of natural gas drilling in New York. We identify four principal catalysts as follows: Catalyst 1: Pressure from Within the State. Although high-volume hydraulic fracturing has become a nationally controversial technology, shale fracturing activity is common in every U.S. state except New York. The regulatory process has delayed potential economic opportunities for state and local economies, as well as many industry stakeholders. In 2010, shale gas production accounted for $18.6 billion in federal royalty and local, state, and federal tax revenues. (1) This is expected to continue to grow substantially. The DEC is under increased pressure to open the state to the same opportunities that Alabama, Arkansas, California, Colorado, Kansas, Louisiana, Montana, New Mexico, North Dakota, Ohio, Oklahoma, Pennsylvania, South Dakota, Texas, Utah, West Virginia, and Wyoming are pursuing. Positive labor market impacts are another major economic draw. According to the Revised Draft SGEIS on the Oil, Gas and Solution Mining Regulatory Program (September 2011), hydraulic fracturing would create between 4,408 and 17,634 full-time equivalent (FTE) direct construction jobs in New York State. Indirect employment in other sectors would add an additional 29,174 FTE jobs. Furthermore, the SGEIS analysis suggests that drilling activities could add an estimated $621.9 million to $2.5 billion in employee earnings (direct and indirect) per year, depending upon how much of the shale is developed. The state would also receive direct tax receipts from leasing land, and has the potential to see an increase in generated indirect revenue. Estimates range from $31 million to $125 million per year in personal income tax receipts, and local governments would benefit from revenue sharing. Some landowner groups say the continued delay in drilling is costing tens of thousands of jobs and millions of dollars in growth for New York, especially in the economically stunted upstate. A number of New York counties near Pennsylvania, such as Chemung, NY, have experienced economic uptick from Pennsylvania drilling activity just across the border. Chemung officials reported that approximately 1,300 county residents are currently employed by the drilling industry in Pennsylvania. The Marcellus shale boom is expected to continue over the next decade and beyond. By 2015, gas drilling activity could bring 20,000 jobs to New York State alone. Other states, such as Pennsylvania and West Virginia, are also expected to see a significant increase in the number of jobs. Catalyst 2: Political Reality of the Moratorium. Oil and gas drilling has taken place in New York since the 19th century, and it remains an important industry with more than 13,000 currently active wells. The use of hydraulic fracturing in particular has been employed for decades. Yet, as technological advancements have enabled access to gas in areas where drilling is not common practice, public concern has ballooned. Opponents argue that more oversight is necessary to protect the environment and public health, while supporters believe the industry is already adequately regulated. Although it is important for New York to complete a thorough environmental and regulatory review, an extended ban could lead to litigation by property owners who have been stripped of the ability to lease their mineral rights. Other states are moving forward by implementing legislative guidelines or rules created by commissions to ensure that resources are developed safely. One of the most controversial issues in other states to date has revolved around the public disclosure of chemical additives in drilling fluid. While the industry is hesitant to reveal trade secrets, the public and many officials want the security of knowing what chemicals are pumped into the ground. Industry transparency could help mitigate the public concern and controversy that is delaying a lift of the moratorium. Currently, at least five other states have set chemical disclosure rules. Arkansas, Michigan, Montana, Texas, and Wyoming require disclosure of the chemical components of drilling fluid. Colorado has the most stringent rules, requiring not just the disclosure of the additives but of their concentrations as well. As more states continue to allow hydraulic fracturing, New York will likely lift the moratorium and instead implement more stringent regulations that help to alleviate public concern surrounding hydraulic fracturing. This will allow the state to safely pursue the expansive opportunities offered by the Marcellus shale without falling behind economically. Catalyst 3: Energy and Infrastructure Benefits. Natural gas provides a key source of energy in the Northeast. The DEC estimates the Marcellus shale gas resource potential to be between 168-516 Tcf. Even at the low end of this range, Marcellus alone could supply seven years of total U.S. energy consumption, and it would provide a local resource for New York. One report suggests that savings from lower natural gas costs would result in an average annual savings of $926 per household. (4) Industry growth is leading to lower natural gas and electric power prices, while decreasing reliance on Liquid Natural Gas (LNG) imports and enhancing domestic energy security. This makes development of the resources an even more attractive commitment to New York. In addition, the natural gas business is predominantly regional in scope. Drilling companies would be required to build new pipelines for gas development in New York, therefore State regulators face valuable ancillary benefits of natural gas development such as infrastructure improvements. Catalyst 4: Technology Improvements. Lastly, the moratorium itself does not prevent the use of alternative drilling technologies, such as non-hydraulic fracturing, for shale gas production. Developers are already using new systems in Texas and Canada, as well as in France where hydraulic fracturing is banned country-wide. Commercial viability of these new technologies could ultimately provide an alternative to jumpstart shale drilling in New York if necessary. The potential benefits from development of the Marcellus shale in New York are undeniable, though regulators are still working to balance the need to stimulate the economy with environmental protection and public health. Since closing the public comment period in January, the DEC has signaled that much more work is needed, making no promises to near-term completion. While, neighboring states are feeling the economic benefits of drilling, the political environment and the recession continues adding pressure to the process in New York state.

03 NATURAL GAS↗

Analysis of Slow Spill Data for the Mu2e Experiment

The execution of the Mu2e experiment requires a stable, low-intensity proton beam from the Delivery Ring to produce clean data and protect equipment. This is done by performing a “slow extraction,” which is the gradual contraction of the stable region within the accelerator’s beam pipe. The Delivery Ring is currently unable to perform slow extraction with the stability required by Mu2e. To resolve this, the FAN-C team is training machine learning models with the purpose of replacing the Delivery Ring’s current PID controllers with AI-powered controllers. Training these models requires clean, processed data from slow spills. Over the course of this project, data from previous slow spills were processed and analyzed, and the clean data, graphs, and insights gained from the process were provided to the FAN-C team to assist them in their efforts.

Osborn, Thomas [Purdue U., West Lafayette]↗

Lessons Learned from PEP-II LLRF and Longitudinal Feedback

The PEP-II B-Factory collider ended the final phase of operation at nearly twice the design current and 4X the design luminosity. To highlight the evolution from the original conceptual design through to the 1.2E34 final machine we choose one example each from the broadband feedback and from the LLRF system. They illustrate the original design estimation missed some very significant details, and how in the course of PEP-II operation unexpected difficulties led to significant insights and new approaches which allowed higher machine performance. We present valuable 'lessons learned' which are of interest to designers of next generation feedback and impedance controlled LLRF systems.

43 PARTICLE ACCELERATORS↗

End-to-End Workflow for Machine-Learning-Based Qubit Readout With QICK and hls4ml

In this article, we present an end-to-end workflow for superconducting qubit readout that embeds codesigned neural networks into the quantum instrumentation control kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx radiofrequency system-on-chip field-programmable gate arrays (FPGAs), we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python application programming interfaces. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA lookup table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.

42 ENGINEERING↗

An Intelligent Metasurface-Based Wireless Power Transfer System

Wireless Power Transfer (WPT) systems are getting more popular in recent years in a wide range of application areas. However, the performance of wireless power transfer systems is adversely affected by coil misalignment and increased power transfer distance. To overcome the limitations, the proposed method in this paper will place an intelligent controllable metasurface between the transmitter and receiver coils. The goal is to establish the feasibility of a metasurface-assisted, intelligent WPT charging system by variable coil design and angle of arrival estimation using machine learning for multiple misalignment cases. We will feed these angles of arrival data to reconfigure the metasurface. The inclusion of a controllable metasurface will improve efficiency and increase the power transfer distance.

Aydin, Emrullah↗

WAMS-Based HVDC Damping Control for Cyber Attack Defense

Owing to the fast and large power regulating the capacity of the HVDC system, the wide-area measurement system (WAMS) based high voltage direct current (HVDC) system has been regarded as a prospective solution to deal with the low-frequency oscillation issue. However, due to the vulnerability of the WAMS communication, WAMS based HVDC system control can be a prime target of malicious penetrations that could lead to disastrous events. To remediate this adverse effect, an improved WAMS based HVDC damping control framework is proposed in this paper. First, a lightweight network named Attack Shuffle convolutional neural Networks (ASNet) is proposed to learn the characteristics of cyber attacks. Then, a model-free-based cyber attack defense framework is introduced to quickly identify the attack types based on the continuous wavelet transform and ASNet. Additionally, an improved control framework of the WAMS and HVDC-based wide-area power oscillation damping control (WH-PODC) is developed to provide different response control for mitigation of the impact of cyber attacks. Finally, the performance of the proposed WH-PODC control framework is evaluated with real PMU data in multiple scenarios in RTDS, where the results indicate that the response intensity can be kept under multiple types of cyber attacks while providing similar effectiveness in oscillation suppression to conventional controls.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Utilizing Genetic Programming to Identify Failures in ICS Networks

Previously, researchers have attempted to apply machine learning techniques to network anomaly detection problems. Due to the staggering amount of variety that can occur in normal networks, the results have often been underwhelming. These challenges are far less pronounced when considering industrial control system (ICS) networks. The recurrent nature of these networks results in less noise and more consistent patterns for a machine learning algorithm to recognize. Here, we propose a method of evolving decision trees through genetic programming (GP) in order to detect network anomalies, such as device outages. Our approach extracts over a dozen features from network packet captures and netflows, normalizes them, and relates them in decision trees using fuzzy logic operators. Furthermore, the trees were used to detect three specific network events from three different points on the network across a statistically significant number of runs and achieved 100% accuracy on five of the nine experiments. When the trees attempted to detect more challenging events at points of presence further from the occurrence, the accuracy averaged to above 98%. Finally, using our method, all of the evolutionary cycles of the GP algorithm are computed a-priori, allowing the best resultant trees to be deployed as semi-real-time sensors with little overhead.

97 MATHEMATICS AND COMPUTING↗

Classification of orthostatic intolerance through data analytics

Imbalance in the autonomic nervous system can lead to orthostatic intolerance manifested by dizziness, lightheadedness, and a sudden loss of consciousness (syncope); these are common conditions, but they are challenging to diagnose correctly. Uncertainties about the triggering mechanisms and the underlying pathophysiology have led to variations in their classification. This study uses machine learning to categorize patients with orthostatic intolerance. Here we use random forest classification trees to identify a small number of markers in blood pressure, and heart rate time-series data measured during head-up tilt to (a) distinguish patients with a single pathology and (b) examine data from patients with a mixed pathophysiology. Next, we use Kmeans to cluster the markers representing the time-series data. We apply the proposed method analyzing clinical data from 186 subjects identified as control or suffering from one of four conditions: postural orthostatic tachycardia (POTS), cardioinhibition, vasodepression, and mixed cardioinhibition and vasodepression. Classification results confirm the use of supervised machine learning. We were able to categorize more than 95% of patients with a single condition and were able to subgroup all patients with mixed cardioinhibitory and vasodepressor syncope. Clustering results confirm the disease groups and identify two distinct subgroups within the control and mixed groups. The proposed study demonstrates how to use machine learning to discover structure in blood pressure and heart rate time-series data. The methodology is used in classification of patients with orthostatic intolerance. Diagnosing orthostatic intolerance is challenging, and full characterization of the pathophysiological mechanisms remains a topic of ongoing research. This study provides a step toward leveraging machine learning to assist clinicians and researchers in addressing these challenges.

60 APPLIED LIFE SCIENCES↗

Detection of Outliers in LiDAR Data Acquired by Multiple Platforms over Sorghum and Maize

High-resolution point cloud data acquired with a laser scanner from any platform contain random noise and outliers. Therefore, outlier detection in LiDAR data is often necessary prior to analysis. Applications in agriculture are particularly challenging, as there is typically no prior knowledge of the statistical distribution of points, plant complexity, and local point densities, which are crop-dependent. The goals of this study were first to investigate approaches to minimize the impact of outliers on LiDAR acquired over agricultural row crops, and specifically for sorghum and maize breeding experiments, by an unmanned aerial vehicle (UAV) and a wheel-based ground platform; second, to evaluate the impact of existing outliers in the datasets on leaf area index (LAI) prediction using LiDAR data. Two methods were investigated to detect and remove the outliers from the plant datasets. The first was based on surface fitting to noisy point cloud data via normal and curvature estimation in a local neighborhood. The second utilized the PointCleanNet deep learning framework. Both methods were applied to individual plants and field-based datasets. To evaluate the method, an F-score was calculated for synthetic data in the controlled conditions, and LAI, the variable being predicted, was computed both before and after outlier removal for both scenarios. Results indicate that the deep learning method for outlier detection is more robust than the geometric approach to changes in point densities, level of noise, and shapes. The prediction of LAI was also improved for the wheel-based vehicle data based on the coefficient of determination (R2) and the root mean squared error (RMSE) of the residuals before and after the removal of outliers.

36 MATERIALS SCIENCE↗

Use Machine Learning to Improve Burnup Measurement in Pebble Bed Reactors

Advanced pebble bed reactor (PBR) designs post new challenges in material control and accountancy (MC&A) because the fuel materials, distributed in many discrete pebbles, are continuously circulated through the reactor core and the refueling path compared to the bulk fuel assembly design in conventional reactors, e.g., light water reactors. In pebble bed reactors, there are hundreds of thousands of fuel pebbles in the reactor core during the normal operation, and the burnup of each pebble is measured when ejected from the core. Accurate burnup measurement is an important step in material control and spent fuel disposition. The measurement is usually based on detection of radiation signatures of fission products accumulated in the pebble fuel over irradiation in the core. Previous research has shown that height of photopeaks of fission products, such as 134 Cs, 137 Cs, 154 Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of pebbles undergoing burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Machine learning-enhanced MPC for demand flexibility in small commercial buildings: An experimental study

Small- and medium-sized commercial buildings (SMCBs) represent the majority of U.S. commercial building stock and a significant share of peak electricity demand, yet they often lack centralized building automation systems, representing a significant untapped resource for urban energy management. This infrastructure gap makes advanced control implementation challenging, limiting the potential for widespread demand flexibility. Model Predictive Control (MPC) has shown strong potential for load shifting, peak demand reduction, and cost savings, but its effectiveness is hindered by unmeasured disturbances such as internal heat gains. This paper presents a Hybrid MPC framework that integrates a physics-based gray-box building thermal model, identified using a lumped disturbance (LD) approach, with a machine learning (ML) model for forecasting unmeasured disturbances. The hybrid approach is designed for buildings with multiple individually controlled heat pump and thermostat pairs, common in SMCBs, and aims to optimize coordinated scheduling of multiple heat pumps under dynamic electricity pricing while respecting comfort constraints. The methodology is validated through both simulations of case study buildings and experimental studies at a highly-instrumented test facility. Simulation results show that the Hybrid MPC achieves substantial load shifting and peak demand reduction, approaching the performance of an ideal MPC with perfect disturbance knowledge, and outperforming a conventional MPC without disturbance forecasting. In experiments, the Hybrid MPC reduced daily HVAC energy costs by 8.7%, peak-price time load (load shifting) by 41.7%, and peak demand by 29.2% compared to baseline control, demonstrating comparable benefits to the 11.6% cost savings, 42.9% load shifting, and 23.2% peak reduction of the ideal MPC. These results demonstrate that the proposed hybrid modeling approach can significantly improve MPC performance in real-world SMCB applications without requiring additional disturbance measurements.

Demand Flexibility↗