A Novel Framework Based on CNN-LSTM Neural Network for Prediction of Missing Values in Electricity Consumption Time-Series Datasets
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Adopting Internet of Things (IoT)-based technologies in smart homes helps users analyze home applianceselectricity consumption for better overall cost monitoring. The IoT application like smart home system (SHS)could suffer from large missing values gaps due to several factors such as security attacks, sensor faults, orconnection errors. In this paper, a novel framework has been proposed to predict large gaps of missing valuesfrom the SHS home appliances electricity consumption time-series datasets. The framework follows a series ofsteps to detect, predict and reconstruct the input time-series datasets of missing values. A hybrid convolutionalneural network-long short term memory (CNN-LSTM) neural network used to forecast large missing valuesgaps. A comparative experiment has been conducted to evaluate the performance of hybrid CNN-LSTM withits single variant CNN and LSTM in forecasting missing values. The experimental results indicate a performancesuperiority of the CNN-LSTM model over the single CNN and LSTM neural networks.
Abstract
Adopting Internet of Things (IoT)-based technologies in smart homes helps users analyze home applianceselectricity consumption for better overall cost monitoring. The IoT application like smart home system (SHS)could suffer from large missing values gaps due to several factors such as security attacks, sensor faults, orconnection errors. In this paper, a novel framework has been proposed to predict large gaps of missing valuesfrom the SHS home appliances electricity consumption time-series datasets. The framework follows a series ofsteps to detect, predict and reconstruct the input time-series datasets of missing values. A hybrid convolutionalneural network-long short term memory (CNN-LSTM) neural network used to forecast large missing valuesgaps. A comparative experiment has been conducted to evaluate the performance of hybrid CNN-LSTM withits single variant CNN and LSTM in forecasting missing values. The experimental results indicate a performancesuperiority of the CNN-LSTM model over the single CNN and LSTM neural networks.
참고문헌 (31)
- Naser Hossein Motlagh, "Internet of Things (IoT) and the Energy Sector", Energies, 13(2), pp.494~ (2020), MDPI AG[DOI]
- Md Arafatur Rahman, "The Emergence of Internet of Things (IoT): Connecting Anything, Anywhere", Computers, 8(2), pp.40~ (2019), MDPI AG[DOI]
- C. Paul, "An overview of IoT based smart homes", Proceedings of 2018 2nd International Conference on Inventive Systems and Control (ICISC), pp.43~46 (2018)
- T. Banerjee, "IoT quality control for data and application needs", IEEE Intelligent Systems, 32(2), pp.68~73 (2017)
- 강현, "The prevention and handling of the missing data", Korean Journal of Anesthesiology, 64(5), pp.402~406 (2013), 대한마취통증의학회
- A. N. Baraldi, "An introduction to modern missing data analyses", Journal of School Psychology, 48(1), pp.5~37 (2010)
- D. Sovilj, "Extreme learning machine for missing data using multiple imputations", Neurocomputing, 174, pp.220~231 (2016)
- P. E. Bunney, "Orexin activation counteracts decreases in nonexercise activity thermogenesis(NEAT)caused by high-fat diet", Physiology & Behavior, 176, pp.139~148 (2017)
- J. Poulos, "Missing data imputation for supervised learning", Applied Artificial Intelligence, 32(2), pp.186~196 (2018)
- X. Xu, "MIAEC : missing data imputation based on the evidence chain", IEEE Access, 6, pp.12983~12992 (2018)
- I. Lana, "On the imputation of missing data for road traffic forecasting : new insights and novel techniques", Transportation Research Part C : Emerging Technologies, 90, pp.18~33 (2018)
- S. Sridevi, "Imputation for the analysis of missing values and prediction of time series data", Proceedings of 2011 International Conference on Recent Trends in Information Technology (ICRTIT), pp.1158~1163 (2011)
- T. A. Mohamed, "Forward and backward forecasting ensembles for the estimation of time series missing data", ANNPR 2014: Artificial Neural Networks in Pattern Recognition, pp.93~104 (2014)
- S. F. Wu, "Time series forecasting with missing values", Proceedings of 20151st International Conference on Industrial Networks and Intelligent Systems (INISCom), pp.151~156 (2015)
- A. S. Dhevi, "Imputing missing values using inverse distance weighted interpolation for time series data", Proceedings of 2014 6th International Conference on Advanced Computing (ICoAC), pp.255~259 (2014)
- E. P. Caillault, "Dynamic time warping-based imputation for univariate time series data", Pattern Recognition Letters, 139, pp.139~147 (2020)
- N. Bokde, "A novel imputation methodology for time series based on pattern sequence forecasting", Pattern Recognition Letters, 116, pp.88~96 (2018)
- Z. Ding, "Comparison of estimating missing values in IoT time series data using different interpolation algorithms", International Journal of Parallel Programming, 48, pp.534~548 (2020)
- Aizaz Chaudhry, "A Method for Improving Imputation and Prediction Accuracy of Highly Seasonal Univariate Data with Large Periods of Missingness", Wireless Communications and Mobile Computing, 2019, pp.1~13 (2019), Hindawi Limited[DOI]
- Taeyoung Kim, "Analysis and Impact Evaluation of Missing Data Imputation in Day-ahead PV Generation Forecasting", Applied Sciences, 9(1), pp.204~ (2019), MDPI AG[DOI]
- N. Al-Milli, "Hybrid neural network to impute missing data for IoT applications", Proceedings of 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), pp.121~125 (2019)
- K. Zor, "Simple approaches to missing data for energy forecasting applications", Proceedings of the 16th International Conference on Clean Energy (ICCE) (2018)
- X. Cao, "A data-driven hybrid optimization model for short-term residential load forecasting", Proceedings of 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing;Pervasive Intelligence and Computing, pp.283~287 (2015)
- T. Y. Kim, "Predicting residential energy consumption using CNN-LSTM neural networks", Energy, 182, pp.72~81 (2019)
- Xiaorui Shao, "Accurate Deep Model for Electricity Consumption Forecasting Using Multi-channel and Multi-Scale Feature Fusion CNN–LSTM", Energies, 13(8), pp.1881~ (2020), MDPI AG[DOI]
- J. Du Preez, "Univariate versus multivariate time series forecasting : an application to international tourism demand", International Journal of Forecasting, 19(3), pp.435~451 (2003)
- Ke Yan, "Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy", Energies, 11(11), pp.3089~ (2018), MDPI AG[DOI]
- M. Massaoudi, "Short-term electric load forecasting based on data-driven deep learning techniques", Proceedings of the 46th Annual Conference of the IEEE Industrial Electronics Society (IECON), pp.2565~2570 (2020)
- "Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks" (2019)[URL]
- C. Nichiforov, "Energy consumption forecasting using ARIMA and neural network models", Proceedings of 2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE), pp.1~4 (2017)
- F. Kaytez, "Forecasting electricity consumption : a comparison of regression analysis, neural networks and least squares support vector machines", International Journal of Electrical Power & Energy Systems, 67, pp.431~438 (2015)