HYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation †
Abstract
:1. Introduction
2. Related Work
3. Problem Formulation
4. HYDROSAFE Architecture
5. SUPs Extraction and Smoothing
5.1. SUPs Extraction
5.2. SUPs Smoothing
6. Extraction of SUPs Features
6.1. Estimation of State Edges
6.2. Determining SUP States
7. SUP Clustering
8. Generating Synthetic SUPs
8.1. The White Noise Component
8.2. The Switch-On Surge Component
8.3. The Ripple Component
8.4. State Edge Position Variation
9. Evaluation
9.1. Evaluating the Effect of the White Noise Component
9.2. Evaluating the Effect of the Switch-On Surge Component
9.3. Evaluating the Effect of the Ripple Component
9.4. Evaluating the Effect of the State Edge Position Variation
10. Conclusions and Future Work
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Nomenclature
Set of households | |
h | Single household |
Set of appliances of h | |
a | Single appliance |
Set of operation modes for a | |
p | Operation mode (AOM) |
Set of days | |
d | Single day |
Daily power consumption sequence | |
instantaneous power sample value | |
Last sample index in d | |
Sampling frequency | |
t | Time |
Set of SUPs in d | |
Single Use Profile (SUP) activated with p | |
Smoothed SUP | |
Set of synthetic SUPs for a | |
Length of sequence s | |
Sample index when appliance is turned on | |
Sample index when appliance is turned off | |
Empty sequence | |
HYDROSAFE generator function | |
Set of tuning parameters | |
Stand-by power threshold | |
Moving median smoother function | |
W | Sliding window size |
Minkowski distance between sequences | |
r | Minkowski distance order |
norm of the Minkowski pariwise distance between sequences | |
Indicator vector of | |
Standard deviation of sequence x | |
MDT window size | |
Left partition of the MDT window | |
Right partition of the MDT window | |
Sequence of thick edges for | |
Single thick edge | |
Lower bound of | |
Upper bound of | |
Thick edges threshold | |
Sequence of states for | |
Single state | |
R | Size of |
Left exact edge of | |
Right exact edge of | |
Rising exact edge | |
Falling exact edge | |
Euclidean distance between | |
SUPs clustering algorithm | |
Eps-neighborhood hyperparameter | |
Minimum number of adjacent elements | |
The core set of SUPs | |
The border set of SUPs | |
The outlier set of SUPs | |
directly density-reachable SUPs | |
ℵ | DTW distance matrix |
DTW distance between | |
Normalized pairwise DTW distance between | |
Normalized pairwise distance matrix | |
Mean value | |
Normal distribution | |
Noise coefficient | |
SySUP with added noise | |
Mean DTW distance between a SySUP and corresponding SUPs | |
Mean of standard deviations of DTW distance between a SySUP and corresponding SUPs | |
SySUP with added SOS | |
SOS coefficient | |
SySUP with added ripple | |
Ripple coefficient | |
Ripple amplitude | |
Ripple period length | |
ℓ | Exact Edge Position (EEP) |
SySUP with variant EEPs |
References
- Ahmad, T.; Chen, H. Potential of three variant machine-learning models for forecasting district level medium-term and long-term energy demand in smart grid environment. Energy 2018, 160, 1008–1020. [Google Scholar] [CrossRef]
- Energy, U. Annual Energy Review 2009; US Energy Information Administration: Washington, DC, USA, 2010; pp. 19–53.
- Canada Energy Regulator, Canada’s Energy Future. 2021. Available online: https://bit.ly/3d8vIqH (accessed on 29 May 2023).
- U.S. Energy Information Administration. Annual Energy Outlook 2021. Available online: https://www.eia.gov/outlooks/aeo/ (accessed on 29 May 2023).
- Canada, N.R. Natural Resources Canada, Appliances for Residential Use. 2021. Available online: https://bit.ly/3omEb0d (accessed on 29 May 2023).
- AlHammadi, A.; AlZaabi, A.; AlMarzooqi, B.; AlNeyadi, S.; AlHashmi, Z.; Shatnawi, M. Survey of IoT-Based Smart Home Approaches. In Proceedings of the 2019 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, 26 March–10 April 2019; IEEE: New York, NY, USA, 2019; pp. 1–6. [Google Scholar]
- Chen, J.; Zhao, Y.; Wang, M.; Wang, K.; Huang, Y.; Xu, Z. Power Sharing and Storage-Based Regenerative Braking Energy Utilization for Sectioning Post in Electrified Railways. IEEE Trans. Transp. Electrif. 2024, 10, 2677–2688. [Google Scholar] [CrossRef]
- Chen, J.; Hu, H.; Wang, M.; Ge, Y.; Wang, K.; Huang, Y.; Yang, K.; He, Z.; Xu, Z.; Li, Y.R. Power flow control-based regenerative braking energy utilization in ac electrified railways: Review and future trends. IEEE Trans. Intell. Transp. Syst. 2024, 25, 6345–6365. [Google Scholar] [CrossRef]
- Gutiérrez-Peña, J.A.; Flores-Arias, J.M.; Bellido-Outeiriño, F.; Lopez, M.O.; Latorre, F.Q. Smart Home Energy Management System and How to Make It Cost Affordable. In Proceedings of the 2020 IEEE 10th International Conference on Consumer Electronics (ICCE-Berlin), Berlin, Germany, 9–11 November 2020; IEEE: New York, NY, USA, 2020; pp. 1–6. [Google Scholar]
- Chen, Y.Y.; Chen, M.H.; Chang, C.M.; Chang, F.S.; Lin, Y.H. A smart home energy management system using two-stage non-intrusive appliance load monitoring over fog-cloud analytics based on Tridium’s Niagara framework for residential demand-side management. Sensors 2021, 21, 2883. [Google Scholar] [CrossRef] [PubMed]
- Jaradat, A.; Lutfiyya, H.; Haque, A. Smart Home Energy Visualizer: A Fusion Of Data Analytics and Information Visualization. IEEE Can. J. Electr. Comput. Eng. 2022, 45, 77–87. [Google Scholar] [CrossRef]
- Shewale, A.; Mokhade, A.; Funde, N.; Bokde, N.D. An Overview of Demand Response in Smart Grid and Optimization Techniques for Efficient Residential Appliance Scheduling Problem. Energies 2020, 13, 4266. [Google Scholar] [CrossRef]
- Chouaib, B.; Lakhdar, D.; Lokmane, Z. Smart Home Energy Management System Architecture Using IoT; ICIST: New York, NY, USA, 2019. [Google Scholar] [CrossRef]
- Jaradat, A.; Lutfiyya, H.; Haque, A. Demand Response for Residential Uses: A Data Analytics Approach. In Proceedings of the 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), New Orleans, LA, USA, 2–16 June 2020; IEEE: New York, NY, USA, 2020; pp. 1–6. [Google Scholar]
- Himeur, Y.; Alsalemi, A.; Bensaali, F.; Amira, A. Building power consumption datasets: Survey, taxonomy and future directions. Energy Build. 2020, 227, 110404. [Google Scholar] [CrossRef]
- Gopinath, R.; Kumar, M.; Joshua, C.P.C.; Srinivas, K. Energy management using non-intrusive load monitoring techniques–State-of-the-art and future research directions. Sustain. Cities Soc. 2020, 62, 102411. [Google Scholar] [CrossRef]
- Thorve, S.; Baek, Y.Y.; Swarup, S.; Mortveit, H.; Marathe, A.; Vullikanti, A.; Marathe, M. High resolution synthetic residential energy use profiles for the United States. Sci. Data 2023, 10, 76. [Google Scholar] [CrossRef]
- Flett, G.; Kelly, N. Modelling of individual domestic occupancy and energy demand behaviours using existing datasets and probabilistic modelling methods. Energy Build. 2021, 252, 111373. [Google Scholar] [CrossRef]
- Marszal-Pomianowska, A.; Heiselberg, P.; Larsen, O.K. Household electricity demand profiles–A high-resolution load model to facilitate modelling of energy flexible buildings. Energy 2016, 103, 487–501. [Google Scholar] [CrossRef]
- Pflugradt, N.; Muntwyler, U. Synthesizing residential load profiles using behavior simulation. Energy Procedia 2017, 122, 655–660. [Google Scholar] [CrossRef]
- Lopez, J.M.G.; Pouresmaeil, E.; Canizares, C.A.; Bhattacharya, K.; Mosaddegh, A.; Solanki, B.V. Smart residential load simulator for energy management in smart grids. IEEE Trans. Ind. Electron. 2018, 66, 1443–1452. [Google Scholar] [CrossRef]
- Kabirifar, M.; Pourghaderi, N.; Rajaei, A.; Moeini-Aghtaie, M.; Safdarian, A. Deterministic and probabilistic models for energy management in distribution systems. In Handbook of Optimization in Electric Power Distribution Systems; Springer: Berlin/Heidelberg, Germany, 2020; pp. 343–382. [Google Scholar]
- Makonin, S.; Wang, Z.J.; Tumpach, C. RAE: The Rainforest Automation Energy Dataset for Smart Grid Meter Data Analysis. arXiv 2017, arXiv:1705.05767. [Google Scholar]
- Happle, G.; Fonseca, J.A.; Schlueter, A. A review on occupant behavior in urban building energy models. Energy Build. 2018, 174, 276–292. [Google Scholar] [CrossRef]
- Kaselimi, M.; Protopapadakis, E.; Voulodimos, A.; Doulamis, N.; Doulamis, A. Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring. Sensors 2022, 22, 5872. [Google Scholar] [CrossRef]
- Sepehr, M.; Eghtedaei, R.; Toolabimoghadam, A.; Noorollahi, Y.; Mohammadi, M. Modeling the electrical energy consumption profile for residential buildings in Iran. Sustain. Cities Soc. 2018, 41, 481–489. [Google Scholar] [CrossRef]
- Widén, J.; Wäckelgård, E. A high-resolution stochastic model of domestic activity patterns and electricity demand. Appl. Energy 2010, 87, 1880–1892. [Google Scholar] [CrossRef]
- Richardson, I.; Thomson, M.; Infield, D.; Clifford, C. Domestic electricity use: A high-resolution energy demand model. Energy Build. 2010, 42, 1878–1887. [Google Scholar] [CrossRef]
- McKenna, E.; Thomson, M. High-resolution stochastic integrated thermal—Electrical domestic demand model. Appl. Energy 2016, 165, 445–461. [Google Scholar] [CrossRef]
- Lombardi, F.; Balderrama, S.; Quoilin, S.; Colombo, E. Generating high-resolution multi-energy load profiles for remote areas with an open-source stochastic model. Energy 2019, 177, 433–444. [Google Scholar] [CrossRef]
- Nilsen, C.B.; Hoff, B.; Østrem, T. Framework for Modeling and Simulation of Household Appliances. In Proceedings of the IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA, 21–23 October 2018; IEEE: New York, NY, USA, 2018; pp. 3472–3476. [Google Scholar]
- Gui, J.; Sun, Z.; Wen, Y.; Tao, D.; Ye, J. A review on generative adversarial networks: Algorithms, theory, and applications. IEEE Trans. Knowl. Data Eng. 2021, 35, 3313–3332. [Google Scholar] [CrossRef]
- Harell, A.; Jones, R.; Makonin, S.; Bajić, I.V. TraceGAN: Synthesizing appliance power signatures using generative adversarial networks. IEEE Trans. Smart Grid 2021, 12, 4553–4563. [Google Scholar] [CrossRef]
- Harell, A.; Jones, R.; Makonin, S.; Bajic, I.V. PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks, 2020. arXiv 2007, arXiv:2007.13645. [Google Scholar]
- Song, L.; Li, Y.; Lu, N. ProfileSR-GAN: A GAN based Super-Resolution Method for Generating High-Resolution Load Profiles. IEEE Trans. Smart Grid 2022, 13, 3278–3289. [Google Scholar] [CrossRef]
- Sanderson, E.; Fragaki, A.; Simo, J.; Matuszewski, B.J. mREAL-GAN: Generating Multiple Residential Electrical Appliance Load Profiles with Inter-Dependencies using a Generative Adversarial Network. arXiv 2021, arXiv:2112.06656. [Google Scholar]
- Liang, X.; Wang, H. Synthesis of realistic load data: Adversarial networks for learning and generating residential load patterns. In Tackling Climate Change with Machine Learning 2022, Proceedings of the NeurIPS 2022 Workshop, Neural Information Processing Systems (NIPS), New Orleans, LO, USA, 28 November–9 December 2022; Mitra, P., Joäo Sousa, M., Roth, M., Drgoňa, J., Strubell, E., Bengio, Y., Eds.; NIPS: San Diego, CA, USA; pp. 1–8.
- Gkoutroumpi, C.; Gkalinikis, N.V.; Vrakas, D. SGAN: Appliance Signatures Data Generation for NILM Applications Using GANs. In Intelligent Computing; Series Title: Lecture Notes in Networks and Systems; Arai, K., Ed.; Springer Nature Switzerland: Cham, Switzerland, 2024; Volume 1018, pp. 325–339. [Google Scholar] [CrossRef]
- Wu, A.N.; Stouffs, R.; Biljecki, F. Generative Adversarial Networks in the built environment: A comprehensive review of the application of GANs across data types and scales. Build. Environ. 2022, 304, 109477. [Google Scholar] [CrossRef]
- Ezhilarasi, P.; Ramesh, L.; Liu, X.; Holm-Nielsen, J.B. Smart Meter Synthetic Data Generator development in python using FBProphet. Softw. Impacts 2023, 15, 100468. [Google Scholar] [CrossRef]
- Li, D.; Bissyandé, T.F.; Kubler, S.; Klein, J.; Le Traon, Y. Profiling household appliance electricity usage with N-gram language modeling. In Proceedings of the 2016 IEEE International Conference on Industrial Technology (ICIT), Taipei, Taiwan, 14–17 March 2016; pp. 604–609. [Google Scholar] [CrossRef]
- Buneeva, N.; Reinhardt, A. AMBAL: Realistic load signature generation for load disaggregation performance evaluation. In Proceedings of the 2017 IEEE International Conference on Smart Grid Communications (Smartgridcomm), Dresden, Germany, 23–27 October 2017; IEEE: New York, NY, USA, 2017; pp. 443–448. [Google Scholar]
- Klemenjak, C.; Kovatsch, C.; Herold, M.; Elmenreich, W. A synthetic energy dataset for non-intrusive load monitoring in households. Sci. Data 2020, 7, 108. [Google Scholar] [CrossRef]
- Chen, D.; Irwin, D.; Shenoy, P. Smartsim: A device-accurate smart home simulator for energy analytics. In Proceedings of the 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm), Sydney, NSW, Australia, 6–9 November 2016; IEEE: New York, NY, USA, 2016; pp. 686–692. [Google Scholar]
- Barker, S.; Mishra, A.; Irwin, D.; Cecchet, E.; Shenoy, P.; Albrecht, J. Smart*: An open data set and tools for enabling research in sustainable homes. SustKDD August 2012, 111, 108. [Google Scholar]
- Henriet, S.; Şimşekli, U.; Fuentes, B.; Richard, G. A generative model for non-intrusive load monitoring in commercial buildings. Energy Build. 2018, 177, 268–278. [Google Scholar] [CrossRef]
- A Simulated High-Frequency Energy Disaggregation Dataset for Commercial Buildings. Available online: https://nilm.telecom-paristech.fr/shed/ (accessed on 24 July 2024).
- Ding, C.H.; Li, T.; Jordan, M.I. Convex and semi-nonnegative matrix factorizations. IEEE Trans. Pattern Anal. Mach. Intell. 2008, 32, 45–55. [Google Scholar] [CrossRef] [PubMed]
- Batra, N.; Kelly, J.; Parson, O.; Dutta, H.; Knottenbelt, W.; Rogers, A.; Singh, A.; Srivastava, M. NILMTK: An open source toolkit for non-intrusive load monitoring. In Proceedings of the 5th International Conference on Future Energy Systems, Cambridge, UK, 11–13 June 2014; pp. 265–276. [Google Scholar]
- Zhao, A.; Chen, M.; Yu, J.; Cui, P. Simulating appliance-level household electricity data: Accounting for residential behavior and usage patterns in China. J. Build. Eng. 2024, 92, 109804. [Google Scholar] [CrossRef]
- Donnal, J. NILM-Synth: Synthetic Dataset Generation for Non-Intrusive Load Monitoring Algorithms. In Proceedings of the 2022 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), New Orleans, LA, USA, 24–28 April 2022; pp. 1–6. [Google Scholar] [CrossRef]
- Meiser, M.; Duppe, B.; Zinnikus, I. SynTiSeD – Synthetic Time Series Data Generator. In Proceedings of the 2023 11th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems (MSCPES), San Antonio, TX, USA, 9 May 2023; pp. 1–6. [Google Scholar] [CrossRef]
- Proedrou, E. A comprehensive review of residential electricity load profile models. IEEE Access 2021, 9, 12114–12133. [Google Scholar] [CrossRef]
- Jaradat, A. Github Repo for HYDROSAFE, 2021. Available online: https://github.com/abedjar/HYDROSAFE (accessed on 29 May 2023).
- Berndt, D.J.; Clifford, J. Using dynamic time warping to find patterns in time series. In Proceedings of the KDD Workshop, Seattle, WA, USA, 31 July–1 August 1994; Volume 10, pp. 359–370. [Google Scholar]
- Menke, W.; Menke, J. Environmental Data Analysis with MatLab; Academic Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Nguyen, T.; Qin, X.; Dinh, A.; Bui, F. Low resource complexity R-peak detection based on triangle template matching and moving average filter. Sensors 2019, 19, 3997. [Google Scholar] [CrossRef]
- An, X.; K. Stylios, G. Comparison of motion artefact reduction methods and the implementation of adaptive motion artefact reduction in wearable electrocardiogram monitoring. Sensors 2020, 20, 1468. [Google Scholar] [CrossRef]
- Tan, P.N.; Steinbach, M.; Kumar, V. Introduction to Data Mining; Pearson Education India: Bangalore, India, 2016. [Google Scholar]
- Patel, K.J. Effects of Transformer Inrush Current. Bachelor’s Thesis, University of Southern Queensland, Toowoomba, QLD, Australia, 2013. [Google Scholar]
- Fried, R. On the robust detection of edges in time series filtering. Comput. Stat. Data Anal. 2007, 52, 1063–1074. [Google Scholar] [CrossRef]
- Jaradat, A.; Alarbi, M.; Lutfiyya, H.; Haque, A. Appliances Operation Modes Identification Using States Clustering. In Proceedings of the 2023 International Conference on Smart Applications, Communications and Networking (SmartNets), Istanbul, Turkiye, 25–27 July 2023; pp. 1–6. [Google Scholar] [CrossRef]
- Jaradat, A.; Lutfiyya, H.; Haque, A. Density And Dynamic Time Warping Based Spatial Clustering For Appliance Operation Modes. In Proceedings of the 2023 IEEE PES Conference on Innovative Smart Grid Technologies-Middle East (ISGT Middle East), Abu Dhabi, United Arab Emirates, 12–15 March 2023; IEEE: New York, NY, USA, 2023; pp. 1–5. [Google Scholar]
- Ester, M.; Kriegel, H.P.; Sander, J.; Xu, X. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the KDD, Portland, OR, USA, 2–5 August 1996; Volume 96, pp. 226–231. [Google Scholar]
Simulator | No. Appliances | Availability | Sampling Rate | Scope | Description |
---|---|---|---|---|---|
Henriet et al. [46] | 66 | Public | 0.033 Hz | Commercial | SHED is a stochastic-based comprehensive framework for energy disaggregation in commercial buildings, including a statistical analysis of differences between commercial and residential buildings, a generative model for simulating high-frequency current waveforms utilizing the Semi Non-negative Matrix Factorization (SNMF) algorithm [48]. |
Chen et al. [44] | 25 | Public | 1 Hz | Residential | SmartSim is a device-accurate, NILM-TK integrated [49], smart home energy trace generator that generates complete datasets for homes with second-level energy data through a generation pipeline that utilizes historical data, Distribution learning, Event marking, and Trace Generation processes. |
Buneeva et al. [42] | 14 | N/A | 1 Hz | Residential | AMBAL is a NILM-TK integrated system for automatically generating realistic synthetic power consumption traces represented as sequences of parameterized signatures, minimizing complexity for desired accuracy. |
Zhao et al. [50] | N/A | N/A | N/A | Residential | A data generation model based on Markov chains and Variational Autoencoders (VAE) to simulate diversified and random electricity consumption data for household appliances, accounting for the residential behavior and usage patterns in Chinese households. |
Thorve et al. [17] | 7 | Public | Hourly | Residential | A large-scale digital-twin dataset of residential energy use for the contiguous United States, featuring synthetic hourly energy use profiles for the U.S. population using census data, statistical methods, activity-related attributes through regression models and survey data. |
Donnal [51] | Variable | Public | Variable | Residential | NILM-Synth is a synthetic dataset generation tool that creates realistic power waveforms by superimposing extracted exemplars from live power data using existing NILM infrastructure. |
Ezhilarasi et al. [40] | N/A | Public | 30 min | N/A | Smart meter-SDG is a Smart Meter Synthetic Data Generator using the FBProphet library based on the UK Power Networks project. |
Meiser et al. [52] | N/A | Public | N/A | Residential | SynTiSeD is a probabilistic multi-agent-based simulation tool that generates synthetic energy data based on real-world data. The model is interactive and involves Behavior Modeling, residents, and appliances into account. |
Klemenjak et al. [43] | 21 | Public | 5 Hz | Residential | SynD is a synthetic energy dataset that is generated using a custom simulation process based on power consumption patterns recorded from real household constantly on, periodical, single-pattern, and multi-pattern appliances in Austria. |
House | Appliance | AOM-1 | AOM-2 | AOM-3 |
---|---|---|---|---|
1 | dryer | 32.704 | 17.23 | 18.74 |
2 | dryer | 77.63 | 203.19 | 208.24 |
1 | dishwasher | 31.92 | 8.45 | - |
2 | dishwasher | 0.76 | - | - |
1 | washer | 10.04 | 9.064 | - |
2 | washer | 7.65 | 9.29 | 6.24 |
House | Appliance | AOM-1 | AOM-2 | AOM-3 |
---|---|---|---|---|
1 | dryer | 44.91 | 5.36 | 17.80 |
2 | dryer | 45.22 | 0.0 | 93.15 |
1 | dishwasher | 30.11 | 4.91 | - |
2 | dishwasher | 0.36 | - | - |
1 | washer | 3.69 | 3.74 | - |
2 | washer | 2.75 | 3.15 | 1.65 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jaradat, A.; Alarbi, M.; Haque, A.; Lutfiyya, H. HYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation. Sensors 2024, 24, 5619. https://doi.org/10.3390/s24175619
Jaradat A, Alarbi M, Haque A, Lutfiyya H. HYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation. Sensors. 2024; 24(17):5619. https://doi.org/10.3390/s24175619
Chicago/Turabian StyleJaradat, Abdelkareem, Muhamed Alarbi, Anwar Haque, and Hanan Lutfiyya. 2024. "HYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation" Sensors 24, no. 17: 5619. https://doi.org/10.3390/s24175619