A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification
Energy consumption is increasing daily, and with that comes a continuous increase in energy costs. Predicting future energy consumption and building an effective energy management system for smart homes has become essential for many industrialists to solve the problem of energy wastage. Machine lear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/127 |
| _version_ | 1797431253461368832 |
|---|---|
| author | Wafa Shafqat Kyu-Tae Lee Do-Hyeun Kim |
| author_facet | Wafa Shafqat Kyu-Tae Lee Do-Hyeun Kim |
| author_sort | Wafa Shafqat |
| collection | DOAJ |
| description | Energy consumption is increasing daily, and with that comes a continuous increase in energy costs. Predicting future energy consumption and building an effective energy management system for smart homes has become essential for many industrialists to solve the problem of energy wastage. Machine learning has shown significant outcomes in the field of energy management systems. This paper presents a comprehensive predictive-learning based framework for smart home energy management systems. We propose five modules: classification, prediction, optimization, scheduling, and controllers. In the classification module, we classify the category of users and appliances by using k-means clustering and support vector machine based classification. We predict the future energy consumption and energy cost for each user category using long-term memory in the prediction module. We define objective functions for optimization and use grey wolf optimization and particle swarm optimization for scheduling appliances. For each case, we give priority to user preferences and indoor and outdoor environmental conditions. We define control rules to control the usage of appliances according to the schedule while prioritizing user preferences and minimizing energy consumption and cost. We perform experiments to evaluate the performance of our proposed methodology, and the results show that our proposed approach significantly reduces energy cost while providing an optimized solution for energy consumption that prioritizes user preferences and considers both indoor and outdoor environmental factors. |
| first_indexed | 2024-03-09T09:42:13Z |
| format | Article |
| id | doaj.art-f4fc56b0cb27484794c5696fd073f641 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:42:13Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f4fc56b0cb27484794c5696fd073f6412023-12-02T00:53:30ZengMDPI AGSensors1424-82202022-12-0123112710.3390/s23010127A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance ClassificationWafa Shafqat0Kyu-Tae Lee1Do-Hyeun Kim2Division of Information and Communication Engineering, Kongju National University, Cheonan 331717, Republic of KoreaDivision of Information and Communication Engineering, Kongju National University, Cheonan 331717, Republic of KoreaComputer Engineering Department, Ara Campus, Jeju National University, Jeju-si 63243, Republic of KoreaEnergy consumption is increasing daily, and with that comes a continuous increase in energy costs. Predicting future energy consumption and building an effective energy management system for smart homes has become essential for many industrialists to solve the problem of energy wastage. Machine learning has shown significant outcomes in the field of energy management systems. This paper presents a comprehensive predictive-learning based framework for smart home energy management systems. We propose five modules: classification, prediction, optimization, scheduling, and controllers. In the classification module, we classify the category of users and appliances by using k-means clustering and support vector machine based classification. We predict the future energy consumption and energy cost for each user category using long-term memory in the prediction module. We define objective functions for optimization and use grey wolf optimization and particle swarm optimization for scheduling appliances. For each case, we give priority to user preferences and indoor and outdoor environmental conditions. We define control rules to control the usage of appliances according to the schedule while prioritizing user preferences and minimizing energy consumption and cost. We perform experiments to evaluate the performance of our proposed methodology, and the results show that our proposed approach significantly reduces energy cost while providing an optimized solution for energy consumption that prioritizes user preferences and considers both indoor and outdoor environmental factors.https://www.mdpi.com/1424-8220/23/1/127energy consumptionenergy costoptimal schedulingsmart homesuser classificationappliance classification |
| spellingShingle | Wafa Shafqat Kyu-Tae Lee Do-Hyeun Kim A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification Sensors energy consumption energy cost optimal scheduling smart homes user classification appliance classification |
| title | A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification |
| title_full | A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification |
| title_fullStr | A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification |
| title_full_unstemmed | A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification |
| title_short | A Comprehensive Predictive-Learning Framework for Optimal Scheduling and Control of Smart Home Appliances Based on User and Appliance Classification |
| title_sort | comprehensive predictive learning framework for optimal scheduling and control of smart home appliances based on user and appliance classification |
| topic | energy consumption energy cost optimal scheduling smart homes user classification appliance classification |
| url | https://www.mdpi.com/1424-8220/23/1/127 |
| work_keys_str_mv | AT wafashafqat acomprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification AT kyutaelee acomprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification AT dohyeunkim acomprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification AT wafashafqat comprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification AT kyutaelee comprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification AT dohyeunkim comprehensivepredictivelearningframeworkforoptimalschedulingandcontrolofsmarthomeappliancesbasedonuserandapplianceclassification |