Abstract
In conjunction with the 4th Industrial Revolution, many industries are implementing systems to collect data on energy consumption to be able to make informed decision on scheduling processes and manufacturing in factories. Companies can now use this historical data to forecast the expected energy consumption for cost management. This research proposes the use of a Temporal Convolutional Neural Network (TCN) with dilated causal convolutional layers to perform forecasting instead of conventional Long-Short Term Memory (LSTM) or Recurrent Neural Networks (RNN) as TCN exhibit lower memory and computational requirements. This approach is also chosen due to traditional regressive methods such as Autoregressive Integrated Moving Average (ARIMA) fails to capture non-linear patterns and features for multi-step time series data. In this research paper, the electrical energy consumption of a factory will be forecasted by implementing a TCN to extract the features and to capture the complex patterns in time series data such daily electrical energy consumption with a limited dataset. The neural network will be built using Keras and TensorFlow libraries in Python. The energy consumption data as training data will be provided by GoAutomate Sdn Bhd. Then, the historical data of economic factors and indexes such as the KLCI will be included alongside the consumption data for neural network training to determine the effects of the economy on industrial energy consumption. The forecasted results with and without the economic data will then be compared and evaluated using Weighted Average Percentage Error (WAPE) and Mean Absolute Percentage Error (MAPE) metrics. The parameters for the neural network will then be evaluated and fined tuned accordingly based on the accuracy and error metrics. This research is able create a CNN to forecast electrical energy consumption with WAPE = 0.083 & MAPE = 0.092, of a factory one (1) week ahead with a small scale dataset with only 427 data points, and has determined that the effects of economic index such as the Bursa Malaysia has no meaningful impact on industrial energy consumption that can be then applied to the forecasting of energy consumption of the factory.
Highlights
An accurate electrical energy consumption forecast is vital to manufacturing industries to run their operations via managing and planning of energy policy [1], operational schedules and manufacturing processes as industrial sectors
This research proposes the use of a Temporal Convolutional Neural Network (TCN) with dilated causal convolutional layers to perform forecasting instead of conventional Long-Short Term Memory (LSTM) or Recurrent Neural Networks (RNN) as TCN exhibit lower memory and computational requirements
This architecture of Convolutional Neural Networks (CNN) are named as Temporal Convolutional Neural Network (TCN) as it is especially suited to handle temporal time-series data
Summary
An accurate electrical energy consumption forecast is vital to manufacturing industries to run their operations via managing and planning of energy policy [1], operational schedules and manufacturing processes as industrial sectors. Li et al used Convolutional Neural Networks (CNN) with the time-series data of electrical consumption for energy forecasting without considering external factors such as the weather and economy [6]. Reliable large data sets are only accessible if the data is available through public domain or companies has already built in infrastructures for data collection As implementing such infrastructures on top of a manufacturing production line is costly, most small-medium enterprises (SME) may not have the capability to implement the data collection and monitoring infrastructure yet or may not even have the capability or financial prowess to maintain the system altogether. Causal convolution is different from standard convolution due to convolutional operation performed to obtain the output does not take future values as inputs [11] This architecture of CNNs are named as Temporal Convolutional Neural Network (TCN) as it is especially suited to handle temporal time-series data. This research is proposed to create an optimized TCN to forecast the electrical energy consumption of a SME’s factory with small data set
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
