Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Agents”

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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗
NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗
NASA NTRSDate not supplied

Environment Adversarial Reinforcement Learning

This paper presents a training method for increasing performance of reinforcement learning agents. The method is named Environment Adversarial Reinforcement Learning. The method requires the reinforcement learning environment to be parameterizeable. Over the course of training, environment parameters are updated in a direction of increasing difficulty for the agent. The direction for these updates is found using a performance prediction network trained on data from tests of the agent under varying environment parameters. The method was tested on a CartPole environment. A 28-58\% improvement in mean return was found when comparing performance to a baseline reinforcement learning algorithm on both easy and hard versions of the task.

machine learning↗
NASA NTRSDate not supplied

Developing Concepts of Operations Using Multi-Step Tool Techniques With Large Language Models

The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.

systems engineering↗
NASA NTRSDate not supplied

Transformation of the NASA Life Sciences Portal to a FAIR Data Point

The FAIR principles emphasize optimizing metadata, the vast majority of which are textual in nature, and often organized into attribute name-value pairs. This uniformity has led to the development of guidelines and best practices for providing programmatic access to scientific data through their metadata, yielding the first iteration of the FAIR Data Point Specifications (FDPS). A key feature of the FDPS is its support for automated agents seeking and fetching data without first needing to learn a plethora of different application programming interfaces. These software agents can interrogate metadata catalogs that adhere to FDPS in a uniform manner because each catalog describes itself and its metadata schema consistently. This approach enhances the sustainability of data retrieval support, allowing systems to refine and update their metadata schemas as needed and without requiring data-seeking software agents to change how they interrogate FDPS catalogs. An essential aspect of the FDPS is the standardization of data catalog semantics, which formalizes concepts such as “metadata” and “metadata service” and links them to other concepts specifications including the Data Catalog Vocabulary (DCAT), a W3C standard that is also the basis of NASA-STD-2831 “Metadata Standard for Data Discoverability,” authored by NASA’s Office of the Chief Information Officer. The FDPS references DCAT (version 2) elements which focus on the distribution of datasets and support the goal of stream-lined catalog integration across repositories for improved data discovery. Additionally, the FDPS also prescribe the use of Linked Data Platform elements for data catalog-metadata record containment descriptions, allowing users to ascertain which data and metadata belong to which catalogs. NASA’s Life Sciences Portal is implementing the FDPS while formalizing its metadata schema to support the accelerated synthesis of knowledge from space life sciences investigations.

platform↗
DOE OSTI2020

Homopiperazine-based catalysts for neutralization of organophosphorus-based compounds

Novel compositions of matter based on homopiperazine precursor materials and forming a homopiperazine-based ligand are disclosed, along with suitable techniques and materials for the synthesis and utilization thereof. In particular various synthetic schemes and techniques for applying the disclosed compositions of matter as a decontaminating agent. The decontaminating agents include homopiperazine-based ligand-metal complexes that are particularly effective at neutralizing toxicity of nerve agents, pesticides, and other toxic organophosphorus-based compounds. In preferred approaches, the homopiperazine-based ligand-metal complexes act as catalysts to facilitate substitution of a leaving group of the organophosphorus-based compound with a functional group that does not permit the organophosphorus-based compound to inactivate acetylcholinesterase upon introduction of the organophosphorus-based compound to a living organism such as insects and mammals. Advantageously, the catalytic homopiperazine-based ligand-metal complexes are formed using inexpensive, readily-available precursor materials, and may be utilized to neutralize toxins without relying on damaging caustic reactants or environmentally unfriendly organic solvents.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Bi-terminal pegylated integrin-binding peptides and methods of use thereof

The present invention provides bi-terminal PEGylated peptide conjugates that target an integrin such as αvβ6 integrin. In particular embodiments, the peptide conjugates of the present invention further comprise a biological agent such as an imaging agent or a therapeutic agent, e.g., covalently attached to one of the PEG moieties. The peptide conjugates of the present invention are particularly useful for imaging a tumor, organ, or tissue and for treating integrin-mediated diseases and disorders such as cancer, inflammatory diseases, autoimmune diseases, chronic fibrosis, chronic obstructive pulmonary disease (COPD), lung emphysema, and chronic wounding skin disease. Compositions and kits containing the peptide conjugates of the present invention find utility in a wide range of applications including, e.g., in vivo imaging and immunotherapy.

Hausner, Sven H.↗
DOE OSTI2021

Materials to improve the performance of lithium and sodium batteries

A lithium or sodium battery includes a cathode containing manganese; an anode containing an active anode material; a separator; an electrolyte; and a transition metal ion sequestration agent; wherein the transition metal ion sequestration agent contains a micron or nano-sized inorganic compound and the transition metal ion sequestration agent is located on and/or within the separator; on and/or within the anode; in the electrolyte; or any combination thereof.

Vissers, Daniel R.↗
DOE OSTI2021

Buffer-free process cycle for CO 2 sequestration and carbonate production from brine waste streams with high salinity

A method includes: (1) using a chelating agent, extracting divalent ions from a brine solution as complexes of the chelating agent and the divalent ions; (2) using a weak acid, regenerating the chelating agent and producing a divalent ion salt solution; and (3) introducing carbon dioxide to the divalent ion salt solution to induce precipitation of the divalent ions as a carbonate salt. Another method includes: (1) combining water with carbon dioxide to produce a carbon dioxide solution; (2) introducing an ion exchanger to the carbon dioxide solution to induce exchange of alkali metal cations included in the ion exchanger with protons included in the carbon dioxide solution and to produce a bicarbonate salt solution of the alkali metal cations; and (3) introducing a brine solution to the bicarbonate salt solution to induce precipitation of divalent ions from the brine solution as a carbonate salt.

Sant, Gaurav↗
DOE OSTI2022

High Temperature, High Pressure Stability of Aqueous Foams for Potential Application in Enhanced Geothermal System (EGS)

Enhanced Geothermal Systems (EGS) are typically constructed by injecting high-pressure water into deep hot dry rocks (HDR) under carefully controlled conditions to create new or re-open existing fractures, which usually uses an immense quantity of water. In lieu, a more sustainable technique is to utilize aqueous foams as fracturing fluid to reduce water consumption and waste-water treatments of conventional hydraulic fracturing. Although foam-based fracturing has shown promising results in oil and gas industries, its feasibility is not demonstrated in EGS conditions that usually involve high temperature and high pressures. One potential barrier of utilizing foams in EGS applications is that foams are thermodynamically unstable and will become more unstable with increasing temperature due to liquid drainage, bubble coarsening, and coalescence. This work focuses on evaluation of the stability of selected aqueous foams under high-temperature and high-pressure conditions. Specifically, foams generated with surfactant alfa olefin sulfonate (AOS) were studied at temperature up to 200oC, while the pressure ranged between 100 psi and 1000 psi. The effect of additional stabilizing agents was also examined, including guar gum, bentonite clay, borate salt crosslinker, silicon dioxide nanoparticles (SiO2), and graphene oxide (GO) dispersion. Results showed that the stabilizing agents can enhance the foam thermal stability. Foams made with AOS and the borate salt crosslinker exhibited the longest half-life of 20 min at 200°C when the pressure was at 1000 psi. Data fitting showed that foam stability decreased exponentially as temperature increased. On the other hand, pressure increased the foam half-life which followed a power model. This study indicates that it may be possible to obtain highly stable foams at high-temperature and high-pressure conditions with appropriate stabilizing agents.

Thakore, Viren↗
DOE OSTI2021

Apparatus and method for recovering an amine solvent from an acid gas stream

A method and apparatus are provided for recovering an amine solvent from an acid gas stream. The apparatus includes a water wash recovery column, a nozzle for spraying water wash and an amine nucleation agent into the water wash recovery column and an inlet port for introducing acid gas into the water wash recovery column adjacent the lower end thereof. The method includes the steps of treating the acid gas stream in the water wash recovery column with a counter-current flow of water wash in an amine nucleation agent, discharging treated acid gas from an upper end of the water wash recovery column and collecting water wash, amine nucleation agent and entrained amine solvent from the acid gas stream and a sump at a lower end of the water wash recovery column.

Irvin, Bradley David↗
DOE OSTI2022

Modular system and method for mercury speciation in a fluid sample

Modular Hg analysis devices and methods are described for use in mercury speciation protocols. Modules can be selected and removably connected to one another to specifically target mercury species in a sample so as to accurately determine the presence or quantity of different mercury species in a fluid sample. Modules can include reductants for reducing inorganic mercury to form elemental mercury and amalgamation agents to capture the elemental mercury. Modules can include filters for capture of particulates as well as capture agents, e.g., solid phase extraction agents, for capture of organic mercury species.

Looney, Brian B.↗
DOE OSTI2022

Bi-terminal pegylated integrin-binding peptides and methods of use thereof

The present invention provides bi-terminal PEGylated peptide conjugates that target an integrin such as αvβ6 integrin. In particular embodiments, the peptide conjugates of the present invention further comprise a biological agent such as an imaging agent or a therapeutic agent, e.g., covalently attached to one of the PEG moieties. The peptide conjugates of the present invention are particularly useful for imaging a tumor, organ, or tissue and for treating integrin-mediated diseases and disorders such as cancer, inflammatory diseases, autoimmune diseases, chronic fibrosis, chronic obstructive pulmonary disease (COPD), lung emphysema, and chronic wounding skin disease. Compositions and kits containing the peptide conjugates of the present invention find utility in a wide range of applications including, e.g., in vivo imaging and immunotherapy.

Hausner, Sven H.↗
DOE OSTI2023

Large-Eddy Simulation of Flow Over Boeing Gaussian Bump Using Multiagent Reinforcement Learning Wall Model: Preprint

We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning. The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall at various computational grid points. It utilizes a wall eddy-viscosity formulation as the boundary condition to apply the modeled wall shear stress. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow. To further assess the robustness of the developed wall model, simulations of flow over the Boeing Gaussian bump are conducted at a Reynolds number of 2 x 10^6, based on the free-stream velocity and the bump width. The results of mean skin friction and pressure on the bump surface, as well as the velocity statistics of the flow field, are compared to those obtained from equilibrium wall model (EQWM) simulations and published experimental data sets. The developed wall model is found to successfully capture the acceleration and deceleration of the turbulent boundary layer on the bump surface, providing better predictions of skin friction near the bump peak and exhibiting comparable performance to the EQWM with respect to the wall pressure and velocity field. We also conclude that the subgrid-scale model is crucial to the accurate prediction of the flow field, in particular the prediction of separation.

boundary layer↗
DOE OSTI2023

Buffer-free process cycle for CO 2 sequestration and carbonate production from brine waste streams with high salinity

A method includes: (1) using a chelating agent, extracting divalent ions from a brine solution as complexes of the chelating agent and the divalent ions; (2) using a weak acid, regenerating the chelating agent and producing a divalent ion salt solution; and (3) introducing carbon dioxide to the divalent ion salt solution to induce precipitation of the divalent ions as a carbonate salt. Another method includes: (1) combining water with carbon dioxide to produce a carbon dioxide solution; (2) introducing an ion exchanger to the carbon dioxide solution to induce exchange of alkali metal cations included in the ion exchanger with protons included in the carbon dioxide solution and to produce a bicarbonate salt solution of the alkali metal cations; and (3) introducing a brine solution to the bicarbonate salt solution to induce precipitation of divalent ions from the brine solution as a carbonate salt.

Sant, Gaurav↗
DOE OSTI2020

Nuclear Decontamination Evolution and Revolution - 20349

Decontamination, one of the oldest practices in the nuclear industry, is about to change. While no single approach to decontamination is appropriate in all situations, decontamination of highly contaminated surfaces is historically viewed as difficult and/or marginally effective and fixatives and strippable coatings are often called on to manage time sensitive contamination control issues. The deferral of proper decontamination can lead to accumulated concentrations of radioactive material increasing the risk of cross-contamination of workers and equipment while also increasing radiation levels, which further discourages decontamination. The results of the subject testing demonstrate that superior decontamination factors are readily achievable and the ALARA benefit of decontamination is viable through advanced decontamination technologies in conjunction with innovative application techniques. The collateral benefits will save countless radiological man-hours and personnel radiological exposure. The appropriate use of radiological decontamination techniques can prevent or limit the adverse effects of highly radioactive contamination in the work area. High levels of radiological contamination are typically associated with some of the most physically demanding work in the nuclear industry. Additionally, working in highly contaminated environments increases the risk of exposure to elevated levels of airborne radioactivity and radiation from the source term of the contamination, particularly in hard to reach areas or complex equipment. Veolia's Alaron Nuclear Services (Alaron), a fully integrated nuclear facility, has provided the nuclear industry waste treatment, consolidation, repackaging, and broad decontamination services for almost 35 years. In looking at solutions for its customers, as well as for their own facility, Alaron has recently collaborated with Environmental Alternatives, Inc. (EAI), which has provided innovative solutions addressing difficult nuclear decontamination and industrial cleaning challenges since 1989. This broad range of experience along with the products to support the work created an ideal partner for Alaron's needs at their facility. The benefits of collaboration were immediately recognizable to the management of both companies although the decontamination challenge was significant. Due to the nature of the services offered, contamination at the Alaron facility is routine. The recent decontamination experience at Alaron utilized an innovative surfactant process that quickly produces remarkably higher decontamination factors for both removable surface contamination and fixed contamination. Considering the time to decontaminate areas historically designated for high radiological hazard work, the results from this decontamination effort not only reduced contamination levels but also significantly lowered exposure rates in the working environment. The relative ease with which the surfactant is applied, combined with extraordinary decontamination test results, indicates the potential to alter current radiological work processes in a way that improves worker comfort, and removes radiological engineering barriers, allowing Alaron to complete complex radiological tasks more efficiently and effectively. In a series of two simple applications of the decontamination agent to contaminated high bay vertical surfaces, as well as a variety of horizontal and vertical surfaces with variable porousness and surface sealants, there was an overall reduction in removable contamination of approximately 73% with a reduction in area dose of approximately 93%. The results indicate additional reduction in fixed contamination with application of the surfactant. These values are much higher than experienced with more traditional decontamination agents. In conjunction with demonstrating EAI's surfactant on room surfaces, additional studies were conducted on complex geometry equipment including waste processing equipment, tools, and heavily contaminated parts normally handled from Alaron's customers. Evaluations were made with straight application of EAI's surfactant as well as adding additional techniques to the treatment which afforded revolutionary improvements in the levels of contamination removed. Successful decontamination with up to 95% reduction in removable contamination with just one application were demonstrated in several of the trials. This paper outlines the planned approach to use this technology, the variety of surfaces and equipment treated, and the results of the decontamination efforts. Furthermore, this paper discusses options for pretreatment of certain heavily contaminated equipment prior to employees handling and/or working with the equipment. The potential for dose saving and the reduced risk of cross-contamination with the added benefit of lower PPE requirements, produces an enormous potential for cost and time savings. Attendees will benefit from Alaron's experiences and more fully understand the capabilities of EAI's decontamination process. With the variety of contamination agents, forms and surfaces on which the technology was demonstrated, the information will be valuable to a broad cross-section of industry users. The significance of this report demonstrates superior decontamination factors are achievable utilizing the next evolution of decontamination technology and that the ALARA benefits of decontamination are available through advanced and modern decontamination efforts. The collateral benefits will save countless radiological man-hours and valuable personnel radiological exposure. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Reinforcement Learning to Enhance Optimal Operation of Resilient Community Energy Systems

This paper presents a novel model-free multi-agent Reinforcement Learning (RL) control method to enhance the resilience of community energy systems in island mode, which coordinates multiple objectives without the necessity of identifying system models that require expert knowledge. Specifically, a community-level coordinator agent is designed to allocate renewable energy resources among different buildings, and multiple building-level agents are developed to optimize load schedules based on limited energy resources and requirements of building loads and occupants’ comfort. In a two-day evaluation, our RL approach demonstrated a similar performance against MPC without requiring system models and formulation of optimization problems as required in MPC.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION↗
DOE OSTI2024

National Modeling of Geothermal District Energy Systems with Ambient-Temperature Loops Using dGeo: Preprint

Geothermal district energy systems (DES) with ambient-temperature loops, also known as thermal energy networks, are one option for decarbonizing space heating and cooling loads. Geothermal fifth-generation DES include an "ambient" temperature thermal loop that connects heat pumps at each building with thermal balancing sources such as geothermal borehole fields. Heating and cooling are provided via a water-source heat pump at each end-user. This project seeks to analyze the nationwide potential for ambient-temperature loop districts by creating a new module within the Distributed Geothermal Market Demand Model (dGeo). dGeo is an agent-based modeling tool for distributed geothermal resources; it can investigate potential on a nationwide or statewide scale using geospatial data for all 50 states and thermal demands for existing buildings. This process allows for high-level estimates of technical and economic potential for ambient-temperature loop districts across the United States. Using GHEDesigner, a lookup table was created to size borehole fields for different thermal loads and ground conditions experienced across the country. A cost and financing structure, along with incentives, were applied. Cost estimates include costs for the distribution network, borehole field installation and operation, and circulation pump operation, while savings are calculated based on agent energy bills. This newly developed module can be used for assessing which areas of the country have the highest potential for agent benefits from ambient-temperature loop installation and assess the impact of different costing and pricing future scenarios. While the code is still under development and nationwide simulations are ongoing, initial results for two states are provided. Future work includes expanding the module to consider mixed residential and commercial districts and considering multiple costing scenarios.

ambient temperature loop↗