TY - JOUR
T1 - Monthly electric load forecasting using transfer learning for smart cities
AU - Jung, Seung Min
AU - Park, Sungwoo
AU - Jung, Seung Won
AU - Hwang, Eenjun
N1 - Funding Information:
Funding: This research was supported in part by the Korea Electric Power Corporation (grant number: R18XA05) and in part by the Energy Cloud R&D Program (grant number: 2019M3F2A1073179) through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT.
PY - 2020/8
Y1 - 2020/8
N2 - Monthly electric load forecasting is essential to efficiently operate urban power grids. Although diverse forecasting models based on artificial intelligence techniques have been proposed with good performance, they require sufficient datasets for training. In the case of monthly forecasting, because just one data point is generated per month, it is not easy to collect sufficient data to construct models. This lack of data can be alleviated using transfer learning techniques. In this paper, we propose a novel monthly electric load forecasting scheme for a city or district based on transfer learning using similar data from other cities or districts. To do this, we collected the monthly electric load data from 25 districts in Seoul for five categories and various external data, such as calendar, population, and weather data. Then, based on the available data of the target city or district, we selected similar data from the collected datasets by calculating the Pearson correlation coefficient and constructed a forecasting model using the selected data. Lastly, we fine-tuned the model using the target data. To demonstrate the effectiveness of our model, we conducted an extensive comparison with other popular machine-learning techniques through various experiments. We report some of the results.
AB - Monthly electric load forecasting is essential to efficiently operate urban power grids. Although diverse forecasting models based on artificial intelligence techniques have been proposed with good performance, they require sufficient datasets for training. In the case of monthly forecasting, because just one data point is generated per month, it is not easy to collect sufficient data to construct models. This lack of data can be alleviated using transfer learning techniques. In this paper, we propose a novel monthly electric load forecasting scheme for a city or district based on transfer learning using similar data from other cities or districts. To do this, we collected the monthly electric load data from 25 districts in Seoul for five categories and various external data, such as calendar, population, and weather data. Then, based on the available data of the target city or district, we selected similar data from the collected datasets by calculating the Pearson correlation coefficient and constructed a forecasting model using the selected data. Lastly, we fine-tuned the model using the target data. To demonstrate the effectiveness of our model, we conducted an extensive comparison with other popular machine-learning techniques through various experiments. We report some of the results.
KW - Deep neural network
KW - Mid-term load forecasting
KW - Monthly electric load forecasting
KW - Pearson correlation coefficient
KW - Smart city
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85090016657&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090016657&partnerID=8YFLogxK
U2 - 10.3390/SU12166364
DO - 10.3390/SU12166364
M3 - Article
AN - SCOPUS:85090016657
VL - 12
JO - Sustainability
JF - Sustainability
SN - 2071-1050
IS - 16
M1 - 6364
ER -