Search NASA⌕ Search

SEARCH · Search NASA

Results for “Q learning”

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 37 records · Page 2

Decentralised demand response market model based on reinforcement learning

A new decentralised demand response (DR) model relying on bi‐directional communications is developed in this study. In this model, each user is considered as an agent that submits its bids according to the consumption urgency and a set of parameters defined by a reinforcement learning algorithm called Q‐learning. The bids are sent to a local DR market, which is responsible for communicating all bids to the wholesale market and the system operator (SO), reporting to the customers after determining the local DR market clearing price. From local markets’ viewpoint, the goal is to maximise social welfare. Four DR levels are considered to evaluate the effect of different DR portions in the cost of the electricity purchase. The outcomes are compared with the ones achieved from a centralised approach (aggregation‐based model) as well as an uncontrolled method. Numerical studies prove that the proposed decentralised model remarkably drops the electricity cost compare to the uncontrolled method, being nearly as optimal as a centralised approach.

Shafie‐Khah, Miadreza↗

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better at higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO 2 , NO x , VOC, PM 10 ) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.

33 ADVANCED PROPULSION SYSTEMS↗

Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control

Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.

Bernstein, Daniel S.↗

More Than 30 000-fold Field Enhancement of Terahertz Nanoresonators Enabled by Rapid Inverse Design

The rapid development of 6G communications using terahertz (THz) electromagnetic waves has created a demand for highly sensitive THz nanoresonators capable of detecting these waves. Among the potential candidates, THz nanogap loop arrays show promising characteristics but require significant computational resources for accurate simulation. This requirement arises because their unit cells are 10 times smaller than millimeter wavelengths, with nanogap regions that are 1 000 000 times smaller. To address this challenge, we propose a rapid inverse design method using physics-informed machine learning, employing double deep Q-learning with an analytical model of the THz nanogap loop array. In ~39 h on a middle-level personal computer, our approach identifies the optimal structure through 200 000 iterations, achieving an experimental electric field enhancement of 32 000 at 0.2 THz, 300% stronger than prior results. In conclusion, our analytical model-based approach significantly reduces the amount of computational resources required, offering a practical alternative to numerical simulation-based inverse design for THz nanodevices.

21 terahertz time-domain spectroscopy↗

Swing Contract-Based Valuation for Distributed Energy Resources in Transactive Energy Systems: A Reinforcement Learning Approach

With the proliferation of distributed energy resources (DERs) and power grids with high fractions of renewable energy, market constructs are evolving to allow DERs to participate in multiple possible markets, at different levels of grid hierarchy. The effective participation of DERs in market environments is aided by swing contract-based pricing mechanisms, whereby DERs have a two-part compensation structure – one for their reservation/commitment and another for performancedriven ex-post payment for their actual mobilization during dispatch. In this paper, we propose a reinforcement learningbased (Q-learning) approach that allows a rational DER agent to select the market it wants to participate in within a composite market environment where individual markets are coordinated by possibly different actors. The proposed Q-learning framework aids DERs in their self-valuation by implicitly maximizing their own payoff through market participation, assuming a swing contract-based compensation structure. We complement our work through simulation-based investigations where factors affecting the DER decision making process, such as parametric uncertainties in market (and grid) environments, are studied.

Naqvi, Syed Ahsan Raza↗

FIRE: A Failure-Adaptive RL Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated between edge servers due to user mobility. Reinforcement Learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like AR/VR and real- time obstacle detection. These rare failures, being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. We introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose FIRE-ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove FIRE-ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (FIRE-ImDQL) and actor critic (FIRE-ImACRE) versions of our algorithm to enhance scalability. Here, we extend our framework to accommodate users with varying risk tolerances of rare failure events. Through trace-driven experiments, we show that FIRE reduces edge computing costs compared to vanilla RL and the greedy baseline in the event of failures.

Edge computing↗

Reinforcement learning method for plug‐in electric vehicle bidding

This study proposes a novel multi‐agent method for electric vehicle (EV) owners who will take part in the electricity market. Each EV is considered as an agent, and all the EVs have vehicle‐to‐grid capability. These agents aim to minimise the charging cost and to increase the privacy of EV owners due to omitting the aggregator role in the system. Each agent has two independent decision cores for buying and selling energy. These cores are developed based on a reinforcement learning (RL) algorithm, i.e. Q‐learning algorithm, due to its high efficiency and appropriate performance in multi‐agent methods. Based on the proposed method, agents can buy and sell energy with the cost minimisation goal, while they should always have enough energy for the trip, considering the uncertain behaviours of EV owners. Numeric simulations on an illustrative example with one agent and a testing system with 500 agents demonstrate the effectiveness of the proposed method.

Najafi, Soroush↗

QUICR-learning for Multi-Agent Coordination

Coordinating multiple agents that need to perform a sequence of actions to maximize a system level reward requires solving two distinct credit assignment problems. First, credit must be assigned for an action taken at time step t that results in a reward at time step t > t. Second, credit must be assigned for the contribution of agent i to the overall system performance. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning. The second credit assignment problem is typically addressed by creating custom reward functions. To address both credit assignment problems simultaneously, we propose the "Q Updates with Immediate Counterfactual Rewards-learning" (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. QUICR-learning is based on previous work on single-time-step counterfactual rewards described by the collectives framework. Results on a traffic congestion problem shows that QUICR-learning is significantly better than a Q-learner using collectives-based (single-time-step counterfactual) rewards. In addition QUICR-learning provides significant gains over conventional and local Q-learning. Additional results on a multi-agent grid-world problem show that the improvements due to QUICR-learning are not domain specific and can provide up to a ten fold increase in performance over existing methods.

Agogino, Adrian K.↗

Reinforcement Learning Approach to Cybersecurity in Space (RELACSS)

Securing satellite groundstations against cyber-attacks is vital to national security missions. However, these cyber threats are constantly evolving. As vulnerabilities are discovered and patched, new vulnerabilities are discovered and exploited. In order to automate the process of discovering existing vulnerabilities and the means to exploit them, a reinforcement learning framework is presented in this report. We demonstrate that this framework can learn to successfully navigate an unknown network and detect nodes of interest despite the presence of a moving target defense. The agent then exfiltrates a file of interest from the node as quickly as possible. This framework also incorporates a defensive software agent that learns to impede the attacking agents progress. This setup allows for the agents to work against each other and improve their abilities. We anticipate that this capability will help uncover unforeseen vulnerabilities and the means to mitigate them. The modular nature of the framework enables users to swap out learning algorithms and modify the reward functions in order to adapt the learning tasks to various use cases and environments. Several algorithms, viz., tabular Q learning, deep Q networks, proximal policy optimization, advantage actor-critic, generative adversarial imitation learning, are explored for the agents and the results highlighted. The agent learns to solve the tasks in a light-weight abstract environment. Once the agent learns to perform sufficiently well, it can be deployed in a minimega virtual machine environment (or a real network) with wrappers that map abstract actions to software commands. The agent also uses a local representation of the actions called a ‘slot-mechanism’. This allows the agent to learn in a certain network and generalize it to different networks. The defensive agent learns to predict the actions taken by an offensive agent and uses that information to anticipate the threat. This information can then either be used to raise an alarm or to take actions to thwart the attack. We believe that with the appropriate reward design, a representative environment, and action set, this framework can be generalized to tackle other cybersecurity tasks. By sufficiently training these agents, we can anticipate vulnerabilities leading to robust future designs. We can also deploy automated defensive agents that can help secure satellite groundstation and their vital national security missions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Assessing Adaptive Irrigation Impacts on Water Scarcity in Nonstationary Environments—A Multi‐Agent Reinforcement Learning Approach

Abstract One major challenge in water resource management is to balance the uncertain and nonstationary water demands and supplies caused by the changing anthropogenic and hydroclimate conditions. To address this issue, we developed a reinforcement learning agent‐based modeling (RL‐ABM) framework where agents (agriculture water users) are able to learn and adjust water demands based on their interactions with the water systems. The intelligent agents are created by a reinforcement learning algorithm adapted from the Q‐learning algorithm. We illustrated this framework in a case study where the RL‐ABM is two‐way coupled with the Colorado River Simulation System (CRSS), a long‐term planning model used for the administration of the Colorado River Basin, for assessing agriculture water uses impacts on water scarcity. Seventy‐eight intelligent agents are simulated, which can be grouped into three categories based on their parameter values: the “aggressive” (swift actions; low regrets), the “forward‐looking conservative” (mild actions; high regrets; fast learning), and the “myopic conservative” (mild actions; median regrets; slow learning). The ABM‐CRSS results showed that the major reservoirs in the Upper Colorado Basin might experience more frequent water shortages due to the increasing water uses compared to the original CRSS results. If the drought continues, the case study also demonstrates that agents can learn and adjust their demands.

Hung, Fengwei↗

Controlling optical-cavity locking using reinforcement learning

Abstract This study applies an effective methodology based on Reinforcement Learning to a control system. Using the Pound–Drever–Hall locking scheme, we match the wavelength of a controlled laser to the length of a Fabry-Pérot cavity such that the cavity length is an exact integer multiple of the laser wavelength. Typically, long-term drift of the cavity length and laser wavelength exceeds the dynamic range of this control if only the laser’s piezoelectric transducer is actuated, so the same error signal also controls the temperature of the laser crystal. In this work, we instead implement this feedback control grounded on Q-Learning. Our system learns in real-time, eschewing reliance on historical data, and exhibits adaptability to system variations post-training. This adaptive quality ensures continuous updates to the learning agent. This innovative approach maintains lock for eight days on average.

47 OTHER INSTRUMENTATION↗

Machine Learning Solutions for a Stable Grid Recovery

Grid operating security studies are typically employed to establish operating boundaries, ensuring secure and stable operation for a range of operation under NERC guidelines. However, if these boundaries are severely violated, existing system security margins will be largely unknown, as would be a secure incremental dispatch path to higher security margins while continuing to serve load. As an alternative to the use of complex optimizations over dynamic conditions, this work employs the use of machine learning to identify a sequence of secure state transitions which place the grid in a higher degree of operating security with greater static and dynamic stability margins. Several reinforcement learning solution methods were developed using deep learning neural networks, including Deep Q-learning, Mu-Zero, and the continuous algorithms Proximal Reinforcement Learning, and Advantage Actor Critic Learning. The work is demonstrated on a power grid with three control dimensions but can be scaled in size and dimensionality, which is the subject of ongoing research.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and robustness to a single point-of-failure. The Alternating Direction Method of Multipliers (ADMM) is a popular distributed optimization algorithm; however, its convergence performance is highly dependent on the selection of penalty parameters, which are usually chosen heuristically. In this work, we use reinforcement learning (RL) to develop an adaptive penalty parameter selection policy for alternating current optimal power flow (ACOPF) problem solved via ADMM with the goal of minimizing the number of iterations until convergence. We train our RL policy using deep Q-learning and show that this policy can result in significantly accelerated convergence (up to a 59% reduction in the number of iterations compared to existing, curvatureinformed penalty parameter selection methods). Furthermore, we show that our RL policy demonstrates promise for generalizability, performing well under unseen loading schemes as well as under unseen losses of lines and generators (up to a 50% reduction in iterations). This work thus provides a proof-of-concept for using RL for parameter selection in ADMM for power systems applications.

alternating current optimal power flow↗

An Online Search Method for Representative Risky Fault Chains Based on Reinforcement Learning and Knowledge Transfer

In the analysis of cascading outages and blackouts in power systems, risky cascading fault chains should be accurately identified in order to do further block or alleviate blackouts. However, the huge computational burden makes online analysis difficult. In this paper, an online search method for representative risky fault chains based on reinforcement learning and knowledge transfer is proposed. This method aims at promoting efficiency by exploiting similarities of adjacent power flow snapshots in operations. After the “representative risky fault chain” is defined, a framework of tree search based on Markov Decision Process and Q-learning is constructed. The knowledge in past runs is accumulated offline and then applied online, with a mechanism of knowledge transition and extension. The proposed learning based approach is verified on an illustrative 39-bus system with different loading levels, and simulations are carried out on a realworld 1000-bus power grid in China to show the effectiveness and efficiency of the proposed approach.

Blackout↗

Optimal carbon storage reservoir management through deep reinforcement learning

Model-based optimization plays a central role in energy system design and management. The complexity and high-dimensionality of many process-level models, especially those used for geosystem energy exploration and utilization, often lead to formidable computational costs when the dimension of decision space is also large. This work adopts elements of recently advanced deep learning techniques to solve a sequential decision-making problem in applied geosystem management. Specifically, a deep reinforcement learning framework was formed for optimal multiperiod planning, in which a deep Q-learning network (DQN) agent was trained to maximize rewards by learning from high-dimensional inputs and from exploitation of its past experiences. To expedite computation, deep multitask learning was used to approximate high-dimensional, multistate transition functions. Both DQN and deep multitask learning are pattern based. As a demonstration, the framework was applied to optimal carbon sequestration reservoir planning using two different types of management strategies: monitoring only and brine extraction. Both strategies are designed to mitigate potential risks due to pressure buildup. Results show that the DQN agent can identify the optimal policies to maximize the reward for given risk and cost constraints. Finally, experiments also show that knowledge the agent gained from interacting with one environment is largely preserved when deploying the same agent in other similar environments.

15 GEOTHERMAL ENERGY↗

Reinforcement learning applied to dilute combustion control for increased fuel efficiency

To reduce the modeling burden for control of spark-ignition engines, reinforcement learning (RL) has been applied to solve the dilute combustion limit problem. Q-learning was used to identify an optimal control policy to adjust the fuel injection quantity in each combustion cycle. A physics-based model was used to determine the relevant states of the system used for training the control policy in a data-efficient manner. The cost function was chosen such that high cycle-to-cycle variability (CCV) at the dilute limit was minimized while maintaining stoichiometric combustion as much as possible. Experimental results demonstrated a reduction of CCV after the training period with slightly lean combustion, contributing to a net increase in fuel conversion efficiency of 1.33%. To ensure stoichiometric combustion for three-way catalyst compatibility, a second feedback loop based on an exhaust oxygen sensor was incorporated into the fuel quantity controller using a slow proportional-integral (PI) controller. The closed-loop experiments showed that both feedback loops can cooperate effectively, maintaining stoichiometric combustion while reducing combustion CCV and increasing fuel conversion efficiency by 1.09%. Finally, a modified cost function was proposed to ensure stoichiometric combustion with a single controller. In addition, the learning period was shortened by half to evaluate the RL algorithm performance on limited training time. Experimental results showed that the modified cost function could achieve the desired CCV targets, however, the learning time was reduced by half and the fuel conversion efficiency increased only by 0.30%.

33 ADVANCED PROPULSION SYSTEMS↗

Proof-of-concept of a reinforcement learning framework for wind farm energy capture maximization in time-varying wind

Here, we present a proof-of-concept distributed reinforcement learning framework for wind farm energy capture maximization. The algorithm we propose uses Q-Learning in a wake-delayed wind farm environment and considers time-varying, though not yet fully turbulent, wind inflow conditions. These algorithm modifications are used to create the Gradient Approximation with Reinforcement Learning and Incremental Comparison (GARLIC) framework for optimizing wind farm energy capture in time-varying conditions, which is then compared to the FLOw Redirection and Induction in Steady State (FLORIS) static lookup table wind farm controller baseline.

17 WIND ENERGY↗

A Reinforcement Learning Approach to Augment Conventional PID Control in Nuclear Power Plant Transient Operation

The ability of nuclear reactors to operate their power conversion cycles more flexibly will enhance their value to energy grids with variable pricing. Current nuclear control systems are typically classical controllers that are often based on proportional-integral-derivative (PID) control. This paper presents a method of augmenting the existing PID control for difficult transient operations in nuclear power plants using a reinforcement learning–derived feedforward signal applied in real time. The agents, which are trained on a test thermal load-following problem, are designed to improve steam generator outlet temperature control for a range of fast load-following scenarios covering ramp rates from 9%/min to 15%/min. Several reinforcement learning algorithms were initially investigated for the training of the feedforward agents with deep Q-learning (DQN) and proximal policy optimization (PPO) networks, which were found to be the most promising. The DQN controllers utilize discrete actions, giving them a better disturbance rejection at steady state but inconsistent response to initial temperature deviations. In contrast, PPO-trained agents, which take continuous actions except for a dead zone around zero, were shown to have the best combination of high disturbance rejection at steady state and good tracking of the desired temperature value. The ability of the PPO agent was also examined, with the average time of decision making found to be on the order of 1 ms. The fault properties of the controller under the loss of the reinforcement learning agent feedforward signal were also examined. The controller showed strong performance in situations of “no-signal” faults. but was less good at handling “stuck-at” faults, where the feedforward signal remains at a set value. In both cases, however, the PID was able to successfully maintain stability, eventually returning the system to a steady state. It is hoped that this work will allow for the proposed control architecture to be examined for more difficult control problems such that it may eventually be used to adapt existing nuclear plants for more aggressive load-following on grids of the future.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗