IMPROVEMENT OF THE MULTI-OBJECTIVE OPTIMIZATION METHOD FOR SMART HOME IoT SYSTEM CONTROL TAKING CYBER RISK INTO ACCOUNT
DOI:
https://doi.org/10.28925/2663-4023.2026.34.1389Keywords:
smart home, Internet of Things, cyber risk, multi-objective optimization, sensor data, proactive control, simulation modelingAbstract
The development of Internet of Things technologies and smart home systems is accompanied by an increasing number of automated decisions based on sensor information. The reliability of these data directly affects control quality because erroneous or intentionally modified measurements may result in inappropriate control actions. This paper proposes a simple improvement of a multi-objective optimization method for smart home IoT control by additionally taking cyber risk into account. The approach is based on a proactive control model in which a control action is selected according to user comfort and energy-efficiency criteria. To increase the resilience of the control process to distorted sensor data, an additional term is introduced into the utility function. This term depends on the level of distrust in the received measurement and on the difference between a candidate control action and a safe action obtained from a trusted state estimate. The distrust level is calculated from the deviation between the current sensor value and an expected value produced by a predictive model or another trusted source. The results section presents the mathematical model of the improved method, a short Python implementation fragment, and the parameters of the simulation experiment. The approach was tested using a 60-day indoor-temperature control simulation with a 15-minute time step. The baseline and improved methods were compared under normal operation and under intentional reduction of temperature sensor readings. Thirty simulation runs were performed. The results show that including cyber risk in the utility function reduces the average number of risky maximum-heating commands from 184.37 to 4.63, which corresponds to a reduction of 97.49%. The improved method maintained thermal comfort for 99.66% of the simulation time, compared with 89.50% for the baseline method under distorted sensor data. The conclusions outline further research directions, including multi-sensor state estimation, adaptive risk weighting, and validation on a physical smart-home testbed.
Downloads
References
Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013). Internet of Things (IoT): A vision, architectural elements, and future directions. Future Generation Computer Systems, 29(7), 1645–1660. https://doi.org/10.1016/j.future.2013.01.010
Karkouch, A., Mousannif, H., Al Moatassime, H., & Noel, T. (2016). Data quality in Internet of Things: A state-of-the-art survey. Journal of Network and Computer Applications, 73, 57–81. https://doi.org/10.1016/j.jnca.2016.08.002
Zhang, A., Song, S., Wang, J., & Yu, P. S. (2017). Time series data cleaning: From anomaly detection to anomaly repairing. Proceedings of the VLDB Endowment, 10(10), 1046–1057. https://doi.org/10.14778/3115404.3115410
Chahuara, P., Portet, F., & Vacher, M. (2017). Context-aware decision making under uncertainty for voice-based control of smart home. Expert Systems with Applications, 75, 63–79. https://doi.org/10.1016/j.eswa.2017.01.014
Cotti, L., Guizzardi, D., Barricelli, B. R., & Fogli, D. (2024). Enabling end-user development in smart homes: A machine learning-powered digital twin for energy efficient management. Future Internet, 16(6), 208. https://doi.org/10.3390/fi16060208
Dobrovolskis, A., Kazanavičius, E., & Kižauskienė, L. (2023). Building XAI-based agents for IoT systems. Applied Sciences, 13(6), 4040. https://doi.org/10.3390/app13064040
Ahmad, R., & Alkhammash, E. H. (2024). Online adaptive Kalman filtering for real-time anomaly detection in wireless sensor networks. Sensors, 24(15), 5046. https://doi.org/10.3390/s24155046
Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58. https://doi.org/10.1145/1541880.1541882
Khan, A. N. (2023). An OCF-IoTivity enabled smart-home optimal indoor environment control system for energy and comfort optimization. Internet of Things, 22, 100712. https://doi.org/10.1016/j.iot.2023.100712
Khan, Q. W., Ahmad, R., Rizwan, A., Khan, A., Lee, K., & Kim, D. (2024). Optimizing energy efficiency and comfort in smart homes through predictive optimization: A case study with indoor environmental parameter consideration. Energy Reports, 11, 5619–5637. https://doi.org/10.1016/j.egyr.2024.05.038
Nishchemenko, D. O., & Aronov, A. O. (2025). Research on methods for optimizing parameters of a smart home control system using IoT. Telecommunication and Information Technologies, 1, 141–150. https://doi.org/10.31673/2412-4338.2025.013027
Nishchemenko, D. O., & Oleinikov, I. A. (2025). Proactive smart home control architecture based on contextual user intentions and multi-objective optimization. Telecommunication and Information Technologies, 3, 141–149. https://doi.org/10.31673/2412-4338.2025.038716
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Андрій Аронов, Вікторія Жебка , Дмитро Ніщеменко , Олексій Ананченко
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
