A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A novel short-term load forecasting framework based on time-series clustering and early classification algorithm
https://orcid.org/0000-0002-2130-2281
https://orcid.org/0000-0001-6037-8193
Highlights A novel short-term load forecasting framework and early classification algorithm are proposed. Dynamic time wrapping k-means and kernel k-means are found to be the best labeling algorithms. Load labels as the extra input features improve forecasting performance. LightGBM is a promising algorithm for short-term load forecasting.
Abstract With the development of data-driven models, extracting information from historical data for better energy forecasting is critically important for energy planning and optimization in buildings. Feature engineering is a key factor in improving the performance of forecasting models. Adding load pattern labels for different daily energy consumption patterns resulting from different time schedules and weather conditions can help improve forecasting accuracy. Traditionally, pattern labeling focuses mainly on finding a day similar to the forecasting day based on calendar or other information, such as weather conditions. The most intuitive approach for dividing historical time-series load into patterns is clustering; however, the pattern cannot be determined before the load is known. To address this problem, this study proposes a novel short-term load forecasting framework integrating an early classification algorithm that uses a stochastic algorithm to predetermine the load pattern of a forecasting day. In addition, a hybrid multistep method combining the strengths of single-step forecasting and recursive multistep forecasting is integrated into the framework. The proposed framework was validated through a case study using actual metered data. The results demonstrate that the early classification and proposed labeling strategy produce satisfactory forecasting accuracy and significantly improve the forecasting performance of the LightGBM model.
A novel short-term load forecasting framework based on time-series clustering and early classification algorithm
https://orcid.org/0000-0002-2130-2281
https://orcid.org/0000-0001-6037-8193
Highlights A novel short-term load forecasting framework and early classification algorithm are proposed. Dynamic time wrapping k-means and kernel k-means are found to be the best labeling algorithms. Load labels as the extra input features improve forecasting performance. LightGBM is a promising algorithm for short-term load forecasting.
Abstract With the development of data-driven models, extracting information from historical data for better energy forecasting is critically important for energy planning and optimization in buildings. Feature engineering is a key factor in improving the performance of forecasting models. Adding load pattern labels for different daily energy consumption patterns resulting from different time schedules and weather conditions can help improve forecasting accuracy. Traditionally, pattern labeling focuses mainly on finding a day similar to the forecasting day based on calendar or other information, such as weather conditions. The most intuitive approach for dividing historical time-series load into patterns is clustering; however, the pattern cannot be determined before the load is known. To address this problem, this study proposes a novel short-term load forecasting framework integrating an early classification algorithm that uses a stochastic algorithm to predetermine the load pattern of a forecasting day. In addition, a hybrid multistep method combining the strengths of single-step forecasting and recursive multistep forecasting is integrated into the framework. The proposed framework was validated through a case study using actual metered data. The results demonstrate that the early classification and proposed labeling strategy produce satisfactory forecasting accuracy and significantly improve the forecasting performance of the LightGBM model.
A novel short-term load forecasting framework based on time-series clustering and early classification algorithm
https://orcid.org/0000-0002-2130-2281
https://orcid.org/0000-0001-6037-8193
Highlights A novel short-term load forecasting framework and early classification algorithm are proposed. Dynamic time wrapping k-means and kernel k-means are found to be the best labeling algorithms. Load labels as the extra input features improve forecasting performance. LightGBM is a promising algorithm for short-term load forecasting.
Abstract With the development of data-driven models, extracting information from historical data for better energy forecasting is critically important for energy planning and optimization in buildings. Feature engineering is a key factor in improving the performance of forecasting models. Adding load pattern labels for different daily energy consumption patterns resulting from different time schedules and weather conditions can help improve forecasting accuracy. Traditionally, pattern labeling focuses mainly on finding a day similar to the forecasting day based on calendar or other information, such as weather conditions. The most intuitive approach for dividing historical time-series load into patterns is clustering; however, the pattern cannot be determined before the load is known. To address this problem, this study proposes a novel short-term load forecasting framework integrating an early classification algorithm that uses a stochastic algorithm to predetermine the load pattern of a forecasting day. In addition, a hybrid multistep method combining the strengths of single-step forecasting and recursive multistep forecasting is integrated into the framework. The proposed framework was validated through a case study using actual metered data. The results demonstrate that the early classification and proposed labeling strategy produce satisfactory forecasting accuracy and significantly improve the forecasting performance of the LightGBM model.
A novel short-term load forecasting framework based on time-series clustering and early classification algorithm
Chen, Zhe (author) / Chen, Yongbao (author) / Xiao, Tong (author) / Wang, Huilong (author) / Hou, Pengwei (author)
Energy and Buildings ; 251
2021-08-17
Article (Journal)
Electronic Resource
English
Short-term load forecasting using time series clustering
| Springer Verlag | 2022
Short term traffic forecasting using time series methods
| Taylor & Francis Verlag | 1988
A novel clustering approach for short-term solar radiation forecasting
| British Library Online Contents | 2015
CAT SWARM OPTIMIZATION BASED CLUSTERING ALGORITHM FOR FUZZY TIME SERIES FORECASTING
| DOAJ | 2019