Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Qingyun Chen et al.
Summary: This paper proposes an intelligent speed control strategy for uncertain cut-in scenarios and introduces a novel training method based on experience screening deep Q-learning network (ES-DQN). Simulation results demonstrate that the proposed strategy outperforms traditional methods in uncertain cut-in scenarios.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Energy & Fuels
Bin Xu et al.
Summary: Reinforcement learning has been applied in optimizing the supervisory control system of an electric vehicle, considering two design targets, energy efficiency and battery life, with the proposed hierarchical Q-learning network showing superior performance compared to baseline methods.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Engineering, Multidisciplinary
Wei Li et al.
Summary: The article introduces a new text-to-image synthesis network architecture T2IGAN, which is automatically searched by neural architecture search (NAS) and efficiently integrates text features and image features with the application of a lightweight transformer, achieving remarkable results.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Mohsen Khosravi et al.
Summary: This paper presents a bi-level mixed-integer linear programming model that considers the optimal scheduling of microgrids and smart homes. The results show that the proposed model reduces operating costs and improves consumers' comfort index.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Mohammed H. Alabdullah et al.
Summary: This paper proposes a deep reinforcement learning-based approach to optimally manage different energy resources within a microgrid. The proposed methodology considers the stochastic behavior of the main elements and formulates the energy management problem as a finite horizon Markov Decision Process (MDP) without prior knowledge of transition probabilities. An efficient reinforcement learning algorithm based on deep Q-networks is implemented to solve the problem. The results of a case study based on a real microgrid demonstrate the effectiveness of the proposed methodology in achieving optimal cost-effective scheduling of energy resources under stochastic conditions.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Victoria J. Hodge et al.
Summary: Mobile robots like drones play a crucial role in surveillance, monitoring, and data collection in buildings, infrastructure, and environments. The research aims to achieve accurate and rapid problem localization through flexible, autonomous, and powerful decision-making mobile robots. The implementation of a generic adaptive navigation algorithm using deep reinforcement learning algorithms aims to improve accuracy and efficiency.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Energy & Fuels
Yan Du et al.
Summary: In this study, a novel deep reinforcement learning method, DDPG, is applied to optimize the HVAC control in residential buildings with the goal of minimizing energy consumption cost while maintaining user comfort. The simulation results demonstrate that the DDPG-based control strategy outperforms the state-of-the-art methods in reducing energy consumption cost and improving comfort level. Additionally, experiments with different building and price models show that the well-trained DDPG-based strategy has high generalization and adaptability for real-world applications.
Review
Computer Science, Interdisciplinary Applications
Zahra Jalilibal et al.
Summary: There are cases where the process mean fluctuates but is still in control, with the process standard deviation being a linear function of the mean. Furthermore, there are situations where the mean and variance of a process are dependent on each other. Researchers have suggested monitoring the Coefficient of Variation as a single statistic in such cases.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Thermodynamics
Armin Cosic et al.
Summary: Local and renewable energy communities have the potential to efficiently utilize distributed energy technologies at regional levels, but face limitations. By using mixed-integer linear programming, challenges in planning can be overcome, leading to economic and ecological benefits for participants.
Article
Green & Sustainable Science & Technology
Chuanshen Wu et al.
Summary: This study focuses on managing uncertainties in microgrids by establishing a two-layer model predictive control strategy with multi-uncertainty sampling for aggregated electric vehicles. Simulation results show that the proposed strategy outperforms conventional strategies in reducing forecasting error and regulating the charging and discharging of EVs.
Article
Engineering, Electrical & Electronic
Chenyu Guo et al.
Summary: This paper proposes a bi-level coordinated optimal energy management framework for distribution system with Multi-MGs, with an interactive mechanism based on a-leader-multi-followers Stackelberg game to improve utility, and investigates a data-driven multi-agent deep reinforcement learning approach to calculate the Stackelberg equilibrium for the OEM problem. The proposed approach is validated through a case study in modified IEEE-33 test systems with multi-MGs.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Article
Green & Sustainable Science & Technology
Leong Kit Gan et al.
Summary: This paper investigates predicting and optimizing the operation of microgrids with a high proportion of variable renewable energy generation. The study experimentally analyses the performance of a Gaussian-process regression forecasting and model predictive control algorithm, demonstrating superior results in an interconnected microgrid environment. Additionally, it is shown that a longer time horizon leads to lower electricity costs but higher battery cycling rates, and improvements in renewable and load forecasts are achieved by sharing information between microgrids.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2021)
Article
Computer Science, Artificial Intelligence
Caomingzhe Si et al.
Summary: This paper proposes an energy management strategy for controllable loads based on reinforcement learning, utilizing mathematical models and two RL algorithms to achieve proper scheduling of home energy resources based on residents' living habits and dependency modes. Through case studies, it is verified that the proposed method can effectively schedule HERs to meet established dependency modes with a relatively small difference from the optimal solution.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Thermodynamics
F. Vitale et al.
Summary: The study focuses on the optimal control strategy and resizing of rSOC microgrids, achieving economic subscaling of rSOC through connection with the grid, leading to reductions in capital expenditure and operating costs.
Article
Automation & Control Systems
Tingyang Meng et al.
Summary: This paper addresses the control problem of battery energy storage systems in microgrid management, solving the issue of balancing the state-of-charge of networked battery units and meeting the total power requirements with distributed control. Two types of estimators are proposed to achieve asymptotic and finite time estimation, showing that SoC balancing of all battery units is achieved under the control laws proposed and the total charging/discharging power of the BESS tracks the desired power. Simulation results validate the theoretical findings.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Article
Construction & Building Technology
Seyyed Mostafa Nosratabadi et al.
Summary: This paper introduces an energy management system that controls distributed energy resources within an entity, presenting a novel convexity principle to address nonlinearity and proposing a robust scenario-based optimization strategy. By conducting a real case study, the effectiveness of the strategy is demonstrated.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Green & Sustainable Science & Technology
Sheraz Aslam et al.
Summary: Microgrids combining renewable energy sources, energy storage devices, and load management methods face challenges due to the intermittent nature of renewables. Forecasting power generation from renewables is crucial for efficient grid operations and optimal resource utilization. Machine learning and deep learning models show promise in predicting energy demand and generation, with the efficiency of forecasting methods depending on historical data availability.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2021)
Article
Construction & Building Technology
Alwyn Mathew et al.
Summary: This paper introduces a Deep Reinforcement Learning model with prioritized experience sampling for appropriate demand response and load shifting optimization, successfully reducing peak power demand and consumer costs.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Engineering, Multidisciplinary
Shiqian Li et al.
Summary: This study introduces an automatically searched Facial Expression Recognition network Auto-FERNet, which solves the issue of inadaptability in traditional methods for FER tasks and proposes a relabeling method based on FES. Experimental results demonstrate the effectiveness of Auto-FERNet in FER tasks with high accuracy.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Miguel A. Velasquez et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Review
Neurosciences
Matthew Botvinick et al.
Article
Energy & Fuels
Md Alamgir Hossain et al.
Review
Energy & Fuels
Muhammad Fahad Zia et al.
Article
Engineering, Electrical & Electronic
Felipe Valencia et al.
IEEE TRANSACTIONS ON SMART GRID
(2016)