Article
Automation & Control Systems
Sami Ben Slama, Marwan Mahmoud
Summary: This paper proposes an advanced Intelligent Home Energy Management (IHEM) approach based on reinforcement learning to achieve home demand response (DR) efficiency. The results show that the proposed optimization method reduces the monthly electricity costs by 20% compared to the Integer Linear Programming (ILP)-based HEMS method.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Yunfei Chu, Zhinong Wei, Guoqiang Sun, Haixiang Zang, Sheng Chen, Yizhou Zhou
Summary: This paper proposes an energy scheduling strategy optimization framework for a home energy management system based on photovoltaic and storage, aiming to reduce environmental impact and costs by scheduling household appliances optimally. Utilizing a Markov decision process model to describe uncertainties in energy usage behavior and real-time electricity prices, a model-free energy scheduling approach based on ACKTR is proposed, with high sampling efficiency.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
M. Firdouse Ali Khan, Ganesh Kumar Chellamani, Premanand Venkatesh Chandramani
Summary: This paper proposes a two-level method to assist the HEM scheme in generating cost-effective schedule-patterns for scheduling home appliances, by identifying comfortable time windows and autonomously generating cost-effective schedule-patterns to reduce user burden.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Chemistry, Analytical
Hanife Apaydin-Ozkan
Summary: AS-REMS is a residential energy management system that reduces electricity costs and peak demand levels while maintaining user comfort. By dividing appliances into controllable classes and considering user preferences, habits, and tariff rates, AS-REMS optimizes appliance scheduling to achieve cost savings and peak demand avoidance. Through the use of the Brute-Force Closest Pair method, AS-REMS successfully balances user comfort with energy efficiency.
Article
Energy & Fuels
Ejaz Ul Haq, Cheng Lyu, Peng Xie, Shuo Yan, Fiaz Ahmad, Youwei Jia
Summary: The feasibility of implementing machine learning methods in home energy management to minimize electricity cost by regulating home electric appliances systems and integrating renewable energy resources is explored in this paper. Simulation-based findings validate the efficiency and reliability of the proposed method without requiring previous information of household electric appliances.
Article
Energy & Fuels
Reda El Makroum, Ahmed Khallaayoun, Rachid Lghoul, Kedar Mehta, Wilfried Zoerner
Summary: This paper presents a home energy management system that optimizes load scheduling for household appliances. Based on the genetic algorithm, the system provides recommendations to improve energy handling based on dynamic pricing, solar energy usage, and user comfort. By leveraging historical appliance usage data, user preferences are integrated into the algorithm. Simulation results based on real-life appliance consumption data show potential cost savings up to 63.48% while maintaining user comfort. The paper also discusses the inclusion of supplementary shiftable loads and limitations of such systems. The main contribution lies in using real data and considering user comfort as a metric in the energy management scheme.
Article
Thermodynamics
Yanxue Li, Zixuan Wang, Wenya Xu, Weijun Gao, Yang Xu, Fu Xiao
Summary: An efficient and flexible energy management strategy is crucial for energy conservation in the building sector. This study proposes a hybrid model-based reinforcement learning framework that uses short-term monitored data to optimize indoor thermal comfort and energy cost-saving performance. Simulation results demonstrate the efficiency and superiority of the proposed framework, with the D3QN agent achieving over 30% cost savings compared to measurement results.
Article
Engineering, Electrical & Electronic
Alireza Ghadertootoonchi, Moein Moeini-Aghtaie, Mehdi Davoudi
Summary: Reinforcement learning (RL) is a subset of artificial intelligence where a decision-making agent tries to act optimally in an environment without the need for identifying and mathematically formulating the environmental constraints. However, RL's performance is affected by environmental complexity. Integrating RL and linear programming (LP) methods reduces the state-action space and improves convergence to the global optimum.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Energy & Fuels
Muhammad Waseem, Zhenzhi Lin, Shengyuan Liu, Zhi Zhang, Tarique Aziz, Danish Khan
Summary: This paper presents an innovative home appliances scheduling framework based on customer preferences, considering demand response and energy storage systems to reduce pollution and fossil fuel usage. By using game theory and fuzzy compromising method, the framework optimizes consumption cost and comfort level while reducing overall energy cost and gaseous emissions.
Article
Engineering, Electrical & Electronic
Murad Khan, Bhagya Nathali Silva, Omar Khattab, Basil Alothman, Chibli Joumaa
Summary: This article introduces a solution to enable transfer learning in smart homes, which eliminates the training time and data requirements for home appliances. By designing mapping functions, correlating datasets, and identifying necessary parameters, knowledge can be transferred between same and different domains, significantly reducing energy consumption.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Aya A. Amer, Khaled Shaban, Ahmed M. Massoud
Summary: This article proposes a data-driven multi-objective DRL-HEMS solution that optimizes household energy consumption, reduces electricity cost, and considers resident comfort and transformer loading condition.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Energy & Fuels
Abdulaziz Almutairi, Naif Albagami, Sultanh Almesned, Omar Alrumayh, Hasmat Malik
Summary: With the increase in electrification trends, household energy consumption is expected to rise significantly. Management of the demand side is necessary to reduce electricity bills and different programs can be introduced, such as real-time pricing. An innovative home appliance scheduling method is proposed, considering rooftop solar panels as energy suppliers. The method is compared with other methods and has shown superiority in terms of energy cost, load ratio, and consumer satisfaction.
Article
Engineering, Electrical & Electronic
Seong-Hyun Hong, Hyun-Suk Lee
Summary: In this paper, we propose a robust EMS algorithm based on safe reinforcement learning to minimize energy costs and ensure energy demands are met in the presence of inconsistent energy supply. The algorithm effectively utilizes short-horizon forecasts on system uncertainties and outperforms other state-of-the-art algorithms in terms of both robustness and cost-efficiency, as demonstrated through experiments using real datasets.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Computer Science, Information Systems
Naoki Kodama, Taku Harada, Kazuteru Miyazaki
Summary: The study proposed an energy management algorithm that utilizes the Dual Targeting Algorithm to strongly learn the experience of acquiring high returns using the quick propagation of delayed rewards via multistep returns. Applied to an HEMS learning experiment, the results showed that the proposed method can reduce the number of hours deviating from the comfort temperature range by about 17% compared to the existing method.
Article
Energy & Fuels
Kezheng Ren, Jun Liu, Zeyang Wu, Xinglei Liu, Yongxin Nie, Haitao Xu
Summary: This paper presents a novel data-driven deep reinforcement learning-based optimization framework for home energy management systems (HEMS) considering uncertain household parameters. By utilizing a thermal comfort evaluation model and a bidirectional gated recurrent unit neural network (BiGRU-NN) prediction model, an optimal decision-making method is established. The experimental results demonstrate that this method can effectively reduce household electricity costs and total costs.
Article
Computer Science, Theory & Methods
Bhagya Nathali Silva, Murad Khan, Kijun Han
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2020)
Article
Telecommunications
Bhagya Nathan Silva, Kyuchang Lee, Yongtak Yoon, Jihun Han, ZhenBo Cao, Kijun Han
Summary: The emergence of smart grid has revolutionized energy consumption patterns and conservation strategies. Household appliance scheduling has gained popularity due to its consideration of sustainable energy and user behaviors. In this study, we propose a least slack time (LST)-based scheduling algorithm with consumption thresholds to minimize electricity cost and maximize user comfort and sustainable energy usage.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2022)
Article
Telecommunications
Muhammad Diyan, Bhagya Nathali Silva, Jihun Han, ZhenBo Cao, Kijun Han
Summary: The increasing demand for electrical energy, smart grid, and renewable energy has created opportunities for Electrical Energy Data Management and Processing Systems (EEDMS). However, implementing and maintaining EEDMS is a challenging task, and the heterogeneous energy data generated from residential and commercial sectors pose challenges for standard IoT architecture. In order to overcome these challenges, a scalable multitasking IoT gateway (IoTGW) is proposed, along with a Data Loading and Storing Module (DLSM) that enables a high dynamic distributed framework.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2022)
Article
Chemistry, Multidisciplinary
Kyuchang Lee, Bhagya Nathali Silva, Kijun Han
APPLIED SCIENCES-BASEL
(2020)
Article
Chemistry, Multidisciplinary
Bhagya Nathali Silva, Murad Khan, Ruchire Eranga Wijesinghe, Samantha Thelijjagoda, Kijun Han
APPLIED SCIENCES-BASEL
(2020)
Article
Chemistry, Analytical
Muhammad Diyan, Murad Khan, Nathali Bhagya Silva, Kijun Han
Article
Chemistry, Multidisciplinary
Zhenbo Cao, Bhagya Nathali Silva, Muhammad Diyan, Jilong Li, Kijun Han
APPLIED SCIENCES-BASEL
(2020)
Article
Computer Science, Information Systems
Ayesha Siddiqa, Muhammad Diyan, Muhammad Toaha Raza Khan, Malik Muhammad Saad, Dongkyun Kim
Summary: The paper proposes a vehicular-content-centric network scheme that uses in-network caching to satisfy content requests. A multihead nomination clustering scheme is introduced to address communication issues, resulting in improved communication rate and cache success ratio.
Article
Engineering, Electrical & Electronic
Daksith Jayasinghe, Chandima Abeysinghe, Ramitha Opanayaka, Randima Dinalankara, Bhagya Nathali Silva, Ruchire Eranga Wijesinghe, Udaya Wijenayake
Summary: The rapid evolution of industrial automation has increased the usage of industrial applications like robot arm manipulation and bin picking. However, the accuracy of object detection and pose estimation in these applications is affected by specular reflections in visual data. This work aims to improve the performance of industrial bin-picking tasks by intelligently removing specular reflections using a deep learning-based neural network model called SpecToPoseNet. The proposed method achieves a significant reduction in the fail rate of object detection compared to other models, making it a positive influence in industrial contexts.
Proceedings Paper
Computer Science, Information Systems
Muhammd Diyan, Murad Khan, Cao Zhenbo, Bhagya Nathali Silva, Jihun Han, Ki Jun Han
Summary: This article proposes an intelligent home energy management system (IHEMS) with a prediction model based on Bi-directional long short Term memory (Bi-LSTM) and an optimization model based on reinforcement learning to address the uncertainty of future energy load and its cost.
35TH INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN 2021)
(2021)
Proceedings Paper
Computer Science, Hardware & Architecture
Muhammad Diyan, Bhagya Nathali Silva, Jihun Han, Kyuchang Lee, Cao Zhenbo, Kijun Han
2020 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE WORKSHOPS (WCNCW)
(2020)