Abstract

This study provides an analysis of papers related to Home Energy Management (HEM) methodology and its potential for optimizing energy consumption in IoT-enabled smart homes. Innovative solutions such as machine learning algorithms, thermal imaging, and IoT sensors are discussed as strategies to improve energy efficiency, reduce waste, and improve security. The importance of sustainable energy systems and cloud-based infrastructures is emphasized, and the need for further development is discussed. The potential of these technologies to reduce carbon emissions and improve energy efficiency while maintaining user comfort levels is highlighted.

Keywords

• 1 Artificial intelligence
• Energy
• IoT
• Smart buildings

1. Introduction

The technology known as Artificial Intelligence is transforming many aspects of our lives at an unparalleled rate, including the way we interact with the world, work, and live. One area where this technology is having a significant impact is in the energy sector. As we move towards more sustainable energy sources and seek to improve energy efficiency, this technology is playing a crucial role in making this transition possible. Its ability to analyze vast amounts of data and provide insights and predictions is enabling AI algorithms to optimize energy usage, reduce waste, and increase the use of renewable energy sources [ 6 ]. From smart energy grids to predictive maintenance of energy systems. It is revolutionizing the way we generate, distribute, and consume energy.

2. Methodology

and

Our study adhered to the Prisma Checklist [ 21 ] involved querying four databases – IEEEXplore [ 17 ], ACM Digital Library [ 18 ], ScienceDirect [ 20 ], and SpringerLink [ 19 ] to gather information on the intersection of Artificial Intelligence and Energy, limited to conference papers published in the past 5 years. This initial search yielded a vast number of articles: 20,155 results in IEEE, 68,317 results in ACM Digital Library, 3,224 results in SpringerLink, and 41,509 results in ScienceDirect. After a careful examination of a few of the research titles, we identified a paper titled "Energy Efficiency in Smart Buildings: IoT Approaches" that drew our attention and prompted us to expand our search criteria by adding the keywords "IoT" and "smart buildings". This led to changes in the number of results retrieved from each database: 46 results in IEEE, 67 in ACM Digital Library, 125 in SpringerLink, and 663 in ScienceDirect, as shown in Figure 1. From these papers, by performing a first pass and then re-analyzing them, we selected 33 papers that piqued our interest for closer inspection. After a thorough review and reading the papers, we selected and analyzed 16 papers that best met our inclusion criteria in terms of their content quality and relevance to the intersection of Artificial Intelligence, IoT, and energy efficiency in smart buildings.

3. State of the art

The Home Energy Management (HEM) methodology offers a new approach to managing energy consumption in IoT-enabled smart homes [ 1 ]. In addition to traditional methods used in energy fields, the HEM methodology aims at optimizing the scheduling of home appliances and improving energy exchange [ 3 ].

As we strive towards a future with renewable energy and Artificial Intelligence, researchers have proposed new ways to optimize energy systems with sophisticated machine learning algorithms and cloud-based infrastructures [ 4 ]. One such proposed system is the SETS system, which aims to enhance security for IoT-based smart homes by detecting energy theft activities with an accuracy of 99.96% using machine learning and statistical models [ 2 ]. However, to truly optimize energy usage, we need to consider the intersection of software development and hardware creation. For example, an IoT device was developed to reduce electricity waste, resulting in lower consumption during a pilot project, and optimized electricity graphs were displayed through a web interface [ 5 ]. In addition, researchers have proposed using thermal imaging with a specific camera and an Android Smartphone to identify insulation issues in buildings with an accuracy of 75% [ 6 ]. Real-time monitoring of building structures can also be achieved using cost-effective resistance sensors implanted during construction to measure moisture content [ 7 ].

Moreover, building occupants' behavior can impact energy efficiency. Therefore, a model using 5 or 8 sensors that collect data every 15 or 20 minutes has been developed to predict occupancy patterns with 90% accuracy [ 8 ]. In the event of a fire outbreak, a smart IoT system with various components can swiftly predict, monitor, and respond by activating alarms, sprinklers, and air exchange systems and notifying relevant personnel in real-time [ 9 ].

By utilizing these innovative technologies, we can work towards a more sustainable future while ensuring the security and efficiency of our energy systems. As we continue to rely more heavily on IoT devices, the energy consumption of smart buildings continues to increase, leading to toxic pollution from electronic waste [ 11 ]. Inefficient energy management in buildings can also contribute to a significant amount of global carbon emissions, accounting for around 30% of these emissions [ 12 ]. To address these challenges, researchers have proposed various innovative solutions. For example, a framework incorporating an algorithm to balance energy consumption and CO2 emissions was developed, reducing emissions by 45-59% while maintaining user comfort levels within a 3% reduction [ 14 ]. Another study addressed the challenge of energy optimization in building management with a transfer learning scheme that utilizes a deep learning model trained on the ImageNet dataset to count people in a room, allowing for more efficient energy usage [ 13 ]. Additionally, an edge-based IoT system was proposed to minimize the daily energy costs of in-home appliances by using a reinforcement learning algorithm, which assists in making appropriate decisions for load scheduling [ 15 ]. Furthermore, comparing various machine learning algorithms resulted in a higher average accuracy of 0.97% and a performance of 0.058% in predicting indoor temperature in smart buildings [ 16 ]. We can see from Table 1, all analyzed papers and their characteristics. [ 1 ], [ 16 ]

Characteristic

AI and ML

4. Conclusion

While the existing energy management systems are inefficient in their task, Artificial Intelligence has significant potential to optimize energy usage and improve sustainability in IoTenabled smart buildings. Some highlights of this potential include machine learning optimization algorithms, thermal imaging, IoT sensors, and other strategies to enhance energy efficiency, reduce waste, and improve security. The importance of further development in sustainable energy systems and cloud-based energy infrastructures cannot be overstated. These innovative solutions offer a promising outlook for the future of energy optimization in smart buildings, with the potential to reduce carbon emissions and improve energy efficiency while ensuring that user comfort levels are maintained. As it is crucial to continue exploring the implementation of these technologies, a more thorough literature review will be conducted in the future.

5. References

References

[1] A. Entezari , A. Aslani , R. Zahedi , and Y. Noorollahi , "Artificial intelligence and machine learning in energy systems: A bibliographic perspective," Energy Strategy Reviews , vol. 45 , pp. 101017 , 2023 .

[2] W. Li , T. Logenthiran , V. -T. Phan and W. L. Woo , "A Novel Smart Energy Theft System (SETS) for IoT-Based Smart Home," in IEEE Internet of Things Journal , vol. 6 , no. 3 , pp. 5531 - 5539 , June 2019 .

[3] sM. M. Iqbal , M. Waseem , A. Manan , R. Liaqat , A. Muqeet and A. Wasaya , "IoT-Enabled Smart Home Energy Management Strategy for DR Actions in Smart Grid Paradigm," 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST) , Islamabad, Pakistan, 2021 , pp. 352 - 357 .

[4] L. D. Mashapu , P. S. P. Eboule and J. -H. C. Pretorius, "The Need for Artificial Intelligence for Energy-Efficiency Management: A Review," 2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE), Ruse , Bulgaria, 2022 , pp. 1 - 6 .

[5] V. Aski , R. S. Shekhawat , S. Mehta , P. K. Jain , and P. Goyal , "IoT Enabled Intelligent Energy Management and Optimization Scheme with Controlling and Monitoring Approach in Modern Classroom Applications," in Intelligent Computing Techniques for Smart Energy Systems , A. Kalam , K. Niazi , A. Soni , S. Siddiqui , and A . Mundra (eds.) , 2020 .

[6] C. K. Metallidou , K. E. Psannis and E. A. Egyptiadou , "Energy Efficiency in Smart Buildings: IoT Approaches," in IEEE Access , vol. 8 ,pp. 63679 - 63699 , 2020 .

[7] N. Khan , N. Pathak and N. Roy , "Detecting Common Insulation Problems in Built Environments using Thermal Images," 2019 IEEE International Conference on Smart Computing (SMARTCOMP) ,Washington, DC, USA, 2019 , pp. 454 - 458 .

[8] M. Sophocleous , P. Savva , M. F. Petrou , J. K. Atkinson and J. Georgiou , "A Durable, ScreenPrinted Sensor for In Situ and Real-Time Monitoring of Concrete's Electrical Resistivity Suitable for Smart Buildings/Cities and IoT," in IEEE Sensors Letters , vol. 2 , no. 4 , pp. 1 - 4 , Dec. 2018 , Art no. 1501404 .

[9] N. Haidar , N. Tamani , F. Nienaber , M. T. Wesseling , A. Bouju and Y. Ghamri-Doudane , "Data Collection Period and Sensor Selection Method for Smart Building Occupancy Prediction," 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring) , Kuala Lumpur, Malaysia , 2019 ,pp. 1 - 6 .

[10] S. Antonov , "Smart Solution for Fire Safety in a Large Garage," 2019 International Conference on Creative Business for Smart and Sustainable Growth (CREBUS), Sandanski , Bulgaria, 2019 , pp. 1 - 4 .

[11] Almalki , F.A. , Alsamhi , S.H. , Sahal , R. et al. Green IoT for Eco-Friendly and Sustainable Smart Cities: Future Directions and Opportunities . Mobile Netw Appl ( 2021 ).

[12] Madsen , S.S. , Santos , A.Q. & Jørgensen , B.N. A QR code based framework for autoconfiguration of IoT sensor networks in buildings . Energy Inform 4 ( Suppl 2 ), 46 ( 2021 ).

[13] Pardamean , B. , Muljo , H.H. , Cenggoro , T.W. et al. Using transfer learning for smart building management system . J Big Data 6 , 110 ( 2019 ).

[14] Constantinou , S. , Konstantinidis , A. , Chrysanthis , P. K. , & Zeinalipour-Yazti , D. ( 2022 ). Green Planning of IoT Home Automation Workflows in Smart Buildings . ACM Trans. Internet Things , 3 ( 4 ), 29 .

[15] Cicirelli , F. , Gentile , A. F. , Greco , E. , Guerrieri , A. , Spezzano , G. , & Vinci , A. ( 2021 ). An Energy Management System at the Edge Based on Reinforcement Learning . In Proceedings of the IEEE/ACM 24th International Symposium on Distributed Simulation and Real Time Applications (pp. 155 - 162 ). IEEE Press.

[16] Alawadi , S. , Mera , D. , Fernández-Delgado , M. et al. A comparison of machine learning algorithms for forecasting indoor temperature in smart buildings . Energy Syst 13 , 689 - 705 ( 2022 ).

[17] IEEExplore.[Online].Available:https://ieeexplo re.ieee.org/Xplore/home.jsp

[18] IACM Digital Library . [Online]. Available: https://dl.acm.org

[19] Springer Link. [Online]. Available: https://link.springer.com

[20] ScienceDirect.com | Science, health and medical journals, full text articles and books . [Online]. Available: https://www.sciencedirect. com

[21] Prisma . [Online]. Available : http://www.prismastatement.org/PRISMAStatement/Checklist.asp x