Real-time forecasting of petrol retail using dilated causal CNNs

• Published in: Journal of ambient intelligence and humanized computing 2022-02, Vol.13 (2), p.989-1000
• Main Authors: Rizvi, Syed M. H., Syed, Tahir, Qureshi, Jalaluddin
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Artificial neural networks; Cloud computing; Computational Intelligence; Datasets; Deep learning; Engineering; Gasoline; Internet of Things; Machine learning; Network latency; Neural networks; Original Research; Performance prediction; Prediction models; Profits; Robotics and Automation; Sales forecasting; Service stations; Smart buildings; Time series; Training; User Interfaces and Human Computer Interaction
• ISSN: 1868-5137; 1868-5145
• DOI: 10.1007/s12652-021-02941-3

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.