Abstract
The recent popularity of smart cities and smart homes has made the adoption of Internet of Things (IoT) devices ubiquitous. Most of these IoT devices are low-end devices with limited capabilities. For neural network based predictive models, the low processing power of connected things is a limitation when training them. In addition, it is still a common practice to deploy these models on cloud servers that possess dedicated high performance computing hardware. However, for IoT applications, it is not feasible to send voluminous raw data to the cloud or a remote backend server on account of high latency, information security concerns or lack of network coverage. In this work, we develop an integrated prediction system for a retail petrol station within the operational constraints of the IoT ecosystem. Our main contribution is the combination of the recent concepts of dilated convolution and the so-called causal convolution into the 1D dilated causal convolutional neural network for time-series prediction. This results in a significantly lightweight model with sound mathematical grounding. Empirical evaluation with a highly-relaxed grid search in the hyperparameter space shows an order-of-magnitude improvement over competing models, both in terms of predictive performance as well as computational cost while training. Compared to state-of-the-art models, our proposed model is able reduce the root mean squared error from 49.38 to 18.37, and training time from 93.07 to 10.21 s on the petrol sales prediction problem.
Similar content being viewed by others
References
Aghajani G, Ghadimi N (2018) Multi-objective energy management in a micro-grid. Energy Rep 4:218–225. https://doi.org/10.1016/j.egyr.2017.10.002
Akbary P, Ghiasi M, Pourkheranjani MRR, Alipour H, Ghadimi N (2019) Extracting appropriate nodal marginal prices for all types of committed reserve. Comput Econ 53(1):1–26. https://doi.org/10.1007/s10614-017-9716-2
Alberg J, Lipton ZC (2017) Improving factor-based quantitative investing by forecasting company fundamentals. arXiv preprint. https://arxiv.org/abs/1711.04837
Anderson E (2011) A new model for cycles in retail petrol prices. Eur J Oper Res 210(2):436–447. https://doi.org/10.1016/j.ejor.2010.10.009
Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint. https://arxiv.org/abs/1803.01271
Carlos RC, Kahn CE, Halabi S (2018) Data science: big data, machine learning, and artificial intelligence. J Am Coll Radiol 15(3):497–498. https://doi.org/10.1016/j.jacr.2018.01.029
Chai J, Wang S, Wang S, Guo J (2012) Demand forecast of petroleum product consumption in the Chinese transportation industry. Energies 5(3):577–598. https://doi.org/10.3390/en5030577
Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Doha, Qatar, pp 1724–1734. https://doi.org/10.3115/v1/D14-1179
Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint. https://arxiv.org/abs/1412.3555
Conneau A, Schwenk H, Barrault L, Lecun Y (2016) Very deep convolutional networks for natural language processing. arXiv preprint. https://arxiv.org/abs/1606.01781
Crone SF, Häger S (2016) Feature selection of autoregressive neural network inputs for trend time series forecasting. In: 2016 International joint conference on neural networks (IJCNN). IEEE, pp 1515–1522. https://doi.org/10.1109/IJCNN.2016.7727378
Dietterich TG (2002) Machine learning for sequential data: a review. In: Caelli T, Amin A, Duin RPW, de Ridder D, Kamel M (eds) Structural, syntactic, and statistical pattern recognition. Springer, Berlin
Gamboa JCB (2017) Deep learning for time-series analysis. arXiv preprint. https://arxiv.org/abs/1701.01887
Jiang L, Hu G (2018) Day-ahead price forecasting for electricity market using long-short term memory recurrent neural network. In: 2018 15th International conference on control, automation, robotics. and vision (ICARCV). IEEE, pp 949–954. https://doi.org/10.1109/ICARCV.2018.8581235
Leng H, Li X, Zhu J, Tang H, Zhang Z, Ghadimi N (2018) A new wind power prediction method based on ridgelet transforms, hybrid feature selection and closed-loop forecasting. Adv Eng Inform 36:20–30. https://doi.org/10.1016/j.aei.2018.02.006
Lia Y, Jiang W, Yang L, Wu T (2018) On neural networks and learning systems for business computing. Neurocomputing 275:1150–1159. https://doi.org/10.1016/j.neucom.2017.09.054
Liu Y, Wang W, Ghadimi N (2017) Electricity load forecasting by an improved forecast engine for building level consumers. Energy 139:18–30. https://doi.org/10.1016/j.energy.2017.07.150
Mirzapour F, Lakzaei M, Varamini G, Teimourian M, Ghadimi N (2019) A new prediction model of battery and wind-solar output in hybrid power system. J Ambient Intell Humaniz Comput 10(1):77–87. https://doi.org/10.1007/s12652-017-0600-7
Mittelman R (2015) Time-series modeling with undecimated fully convolutional neural networks. arXiv preprint. https://arxiv.org/abs/1508.00317
Nguyen HV, Naeem MA, Wichitaksorn N, Pears R (2019) A smart system for short-term price prediction using time series models. Comput Electr Eng 76:339–352. https://doi.org/10.1016/j.compeleceng.2019.04.013
O’Shea K, Nash R (2015) An introduction to convolutional neural networks. arXiv preprint. https://arxiv.org/abs/1511.08458
Rahman MA, Hossain MS, Hassanain E, Muhammad G (2018) Semantic multimedia fog computing and IoT environment: sustainability perspective. IEEE Commun Mag 56(5):80–87. https://doi.org/10.1109/MCOM.2018.1700907
Rajwani A, Syed T, Khan B, Behlim S (2017) Regression analysis for ATM cash flow prediction. In: 2017 International conference on frontiers of information technology (FIT). IEEE, pp 212–217. https://doi.ieeecomputersociety.org/10.1109/FIT.2017.00045
Schmidhuber J, Hochreiter S (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Shafee K, Jale A, Suet Peng Y, Yew KH (2004) Petronas petrol station fuel consumption forecast system (PSFS). In: 2nd International conference on artificial intelligence in engineering and technology (iCAiET 2004), Sabah, Malaysia. http://eprints.utp.edu.my/8711/
Shoaib N, Shamsi JA (2019) Understanding network requirements for smart city applications: challenges and solutions. IT Prof 21(3):33–40. https://doi.org/10.1109/MITP.2018.2883047
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. Adv Neural Inf Process Syst 27:3104–3112
van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: a generative model for raw audio. arXiv preprint. https://arxiv.org/abs/1609.03499
Wang Z, Yan W, Oates T (2017) Time series classification from scratch with deep neural networks: a strong baseline. In: 2017 International joint conference on neural networks (IJCNN), pp 1578–1585. https://doi.org/10.1109/IJCNN.2017.7966039
Younan C (2019) Morrisons slashes the price on petrol and diesel at all UK petrol stations. Daily Star Newspaper. www.dailystar.co.uk/real-life/morrisons-supermarket-fuel-diesel-offer-17215884
Yu L, Wang S, Lai KK (2008) Forecasting crude oil price with an emd-based neural network ensemble learning paradigm. Energy Econ 30(5):2623–2635. https://doi.org/10.1016/j.eneco.2008.05.003
Zhao Z, Fu C, Wang C, Miller CJ (2018) Improvement to the prediction of fuel cost distributions using ARIMA model. In: 2018 IEEE power & energy society general meeting (PESGM), pp 1–5. https://doi.org/10.1109/CIS.2013.145
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rizvi, S.M.H., Syed, T. & Qureshi, J. Real-time forecasting of petrol retail using dilated causal CNNs. J Ambient Intell Human Comput 13, 989–1000 (2022). https://doi.org/10.1007/s12652-021-02941-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-02941-3