4.7 Article

A multi-step predictive deep reinforcement learning algorithm for HVAC control systems in smart buildings

Related references

Note: Only part of the references are listed.
Article Thermodynamics

Multi-feature-scale fusion temporal convolution networks for metal temperature forecasting of ultra-supercritical coal-fired power plant reheater tubes

Linfei Yin et al.

Summary: A multi-feature-scale fusion temporal convolution network prediction model is proposed in this paper for accurate real-time prediction of the metal temperature of reheater tube in a thermal power plant. The model demonstrates strong feature extraction and nonlinear function fitting capabilities, with innovative methods to improve accuracy. The proposed model outperforms 20 other prediction models, achieving higher accuracy in predicting the metal temperature of the reheater tube.

ENERGY (2022)

Article Thermodynamics

A novel flexible grey multivariable model and its application in forecasting energy consumption in China

Meng Zhang et al.

Summary: The objective and accurate prediction of energy consumption is crucial for the implementation of economic policies and energy development strategy by the government. This paper proposes a novel flexible grey multivariable model that captures the dynamic characteristics of the energy system and is compatible with existing grey models. The model is used to predict the energy consumption of three major provinces in China, and demonstrates superior prediction performance compared to competing models.

ENERGY (2022)

Article Thermodynamics

A new prediction model of CO2 diffusion coefficient in crude oil under reservoir conditions based on BP neural network

Hao Chen et al.

Summary: The diffusion coefficient in porous media is crucial for CO2 injection in unconventional oil reservoirs. A neural network model can provide quick and accurate predictions for the diffusion coefficient. Factors such as temperature, pressure, permeability, porosity, and surface area positively correlate with the diffusion coefficient, while oil viscosity, oil density, and volume of porous media negatively correlate with it.

ENERGY (2022)

Article Thermodynamics

Co-benefits of energy efficiency in residential buildings

Amir Baniassadi et al.

Summary: This paper examines a public housing project in Phoenix, AZ, using various tools to calculate economic, environmental, and health metrics associated with three levels of energy efficiency. Results show that energy-saving strategies may significantly improve financial attractiveness when considering health and climate costs.

ENERGY (2022)

Article Thermodynamics

Combined heat and power economic emission dispatch using improved bare-bone multi-objective particle swarm optimization

Guojiang Xiong et al.

Summary: An improved bare-bone multi-objective particle swarm optimization (IBBMOPSO) is proposed to solve the combined heat and power economic emission dispatch problems. The IBBMOPSO integrates four improved strategies to overcome the deficiencies of population diversity and premature convergence in traditional particle swarm optimization. Simulation results demonstrate that IBBMOPSO can achieve higher-quality dispatching schemes with lower generating fuel cost and less pollutant gas emission compared with other algorithms.

ENERGY (2022)

Article Thermodynamics

Location optimization of electric vehicle charging stations: Based on cost model and genetic algorithm

Guangyou Zhou et al.

Summary: This paper examines the challenges faced by the rapid growth of electric vehicles, such as insufficient charging stations, uneven distribution, and high cost. Using Ireland as a case study, the paper develops a social total cost model and an optimization model for charging station locations. Sensitivity analysis reveals that the number of charging stations and the probability of EV charging per day have a significant impact on the total cost.

ENERGY (2022)

Article Thermodynamics

Development of a personalized thermal comfort driven controller for HVAC systems

Cihan Turhan et al.

Summary: The study aims to improve thermal comfort and energy savings in HVAC systems by developing a thermal comfort-driven control algorithm, which was tested in a real building and shown to increase thermal comfort satisfaction by 92% and reduce energy consumption by 13.2% compared to a conventional PID controller. This prototype is cost-effective and easily deployable in real environments, distinguishing it from other existing works in the field.

ENERGY (2021)

Article Thermodynamics

Lifelong control of off-grid microgrid with model-based reinforcement learning

Simone Totaro et al.

Summary: This paper addresses the lifelong control problem of isolated microgrids, proposing a novel model-based reinforcement learning algorithm that can handle system changes and outperforms traditional algorithms.

ENERGY (2021)

Article Engineering, Electrical & Electronic

Multi-task deep reinforcement learning for intelligent multi-zone residential HVAC control

Yan Du et al.

Summary: In this communication, a data-driven deep reinforcement learning method is applied to optimize HVAC users' energy consumption costs while ensuring comfort. By conducting multi-task learning, the efficiency of the deep RL method is enhanced, and its effectiveness and generality in optimizing HVAC operation are verified through comparisons with other algorithms.

ELECTRIC POWER SYSTEMS RESEARCH (2021)

Review Engineering, Electrical & Electronic

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Wojciech Samek et al.

Summary: With the increasing demand for explainable artificial intelligence (XAI) due to the successful usage of machine learning, particularly deep neural networks, this work aims to provide an overview of the field, test interpretability algorithms, and demonstrate successful usage in application scenarios.

PROCEEDINGS OF THE IEEE (2021)

Article Thermodynamics

A hierarchical optimal control strategy for continuous demand response of building HVAC systems to provide frequency regulation service to smart power grids

Huilong Wang et al.

Summary: The study proposes a hierarchical optimal control strategy for utilizing existing HVAC systems in buildings to provide frequency regulation service, optimizing power use baseline and regulation capacity while considering the tradeoff between financial reward and thermal comfort. The strategy is validated on a simulation test platform, showing that it can maximize the use of regulation capacity from HVAC systems while ensuring indoor environment control quality under a given guarantee rate.

ENERGY (2021)

Article Economics

Prediction of the Indian summer monsoon using a stacked autoencoder and ensemble regression model

Moumita Saha et al.

Summary: This study explores the use of deep learning for feature reduction and discovery of predictors for Indian summer monsoon rainfall. The combination of climatic variables as predictors outperforms individual variables, with the model being able to accurately predict the monsoon two months in advance.

INTERNATIONAL JOURNAL OF FORECASTING (2021)

Article Construction & Building Technology

Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network

Zhengbo Zou et al.

BUILDING AND ENVIRONMENT (2020)

Article Computer Science, Information Systems

Deep Reinforcement Learning for Smart Home Energy Management

Liang Yu et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Article Engineering, Electrical & Electronic

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

Weicong Kong et al.

IEEE TRANSACTIONS ON SMART GRID (2019)

Article Automation & Control Systems

Deep Transfer Learning Based on Sparse Autoencoder for Remaining Useful Life Prediction of Tool in Manufacturing

Chuang Sun et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Article Geochemistry & Geophysics

Deep Learning for Hyperspectral Image Classification: An Overview

Shutao Li et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Article Thermodynamics

Model-based predictive control for optimal MicroCSP operation integrated with building HVAC systems

Mohamed Toub et al.

ENERGY CONVERSION AND MANAGEMENT (2019)

Article Computer Science, Information Systems

A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean

Mingxu Han et al.

IEEE ACCESS (2019)

Review Energy & Fuels

Review on the Research and Practice of Deep Learning and Reinforcement Learning in Smart Grids

Dongxia Zhang et al.

CSEE JOURNAL OF POWER AND ENERGY SYSTEMS (2018)

Article Geochemistry & Geophysics

Prediction of Sea Surface Temperature Using Long Short-Term Memory

Qin Zhang et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2017)

Article Engineering, Electrical & Electronic

Generalized Correntropy for Robust Adaptive Filtering

Badong Chen et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2016)

Article Engineering, Electrical & Electronic

Managing Contingencies in Smart Grids via the Internet of Things

Stefano Ciavarella et al.

IEEE TRANSACTIONS ON SMART GRID (2016)

Article Computer Science, Information Systems

A Survey on Demand Response Programs in Smart Grids: Pricing Methods and Optimization Algorithms

John S. Vardakas et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2015)

Article Computer Science, Information Systems

Integrating Cellular Networks, Smart Grid, and Renewable Energy: Analysis, Architecture, and Challenges

Hussein Al Haj Hassan et al.

IEEE ACCESS (2015)

Proceedings Paper Computer Science, Interdisciplinary Applications

An Improved Particle Swarm Optimization Approach for Temperature Control in HVAC for the Purpose of Energy Saving

Zhangjun et al.

MANUFACTURING SCIENCE AND TECHNOLOGY, PTS 1-8 (2012)

Article Engineering, Electrical & Electronic

Quantifying the Effect of Demand Response on Electricity Markets

Chua-Liang Su et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2009)

Article Thermodynamics

Dynamic model of an HVAC system for control analysis

B Tashtoush et al.

ENERGY (2005)