A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Peak demand alert system based on electricity demand forecasting for smart meter data
Highlights A peak demand alerting system for small- and medium-sized enterprises was developed. Only smart meter data and actual weather data are required as input data. The system showed good performance using a BEMS dataset from 273 offices.
Abstract Reducing peak demand is an important cost-saving measure for small and medium enterprises (SMEs) because electricity tariff menus often include a demand charge determined by the yearly highest demand. SMEs are incentivized to reduce the peak demand; thus, information provision services that are suitable for a wide range of SMEs and send alerts about the possibility of exceeding contract demand are needed. We developed a demand forecasting method that incorporated a modified version of support vector regression using only smart meter data and actual weather data as input. We assumed that peak demand alerts are sent to each SME when the forecasted demand exceeds the predefined precaution threshold. The proposed method also has a parameter for intervals of forecasted demand, which controls trade-off between recall and precision of the alerts. Using smart meter data from 273 SMEs, we evaluated the performance of the alerts. Recall was 75.4% for the 1-h-ahead point forecast and 86.9% for the 24-h-ahead interval forecast in one of the best cases.
Peak demand alert system based on electricity demand forecasting for smart meter data
Highlights A peak demand alerting system for small- and medium-sized enterprises was developed. Only smart meter data and actual weather data are required as input data. The system showed good performance using a BEMS dataset from 273 offices.
Abstract Reducing peak demand is an important cost-saving measure for small and medium enterprises (SMEs) because electricity tariff menus often include a demand charge determined by the yearly highest demand. SMEs are incentivized to reduce the peak demand; thus, information provision services that are suitable for a wide range of SMEs and send alerts about the possibility of exceeding contract demand are needed. We developed a demand forecasting method that incorporated a modified version of support vector regression using only smart meter data and actual weather data as input. We assumed that peak demand alerts are sent to each SME when the forecasted demand exceeds the predefined precaution threshold. The proposed method also has a parameter for intervals of forecasted demand, which controls trade-off between recall and precision of the alerts. Using smart meter data from 273 SMEs, we evaluated the performance of the alerts. Recall was 75.4% for the 1-h-ahead point forecast and 86.9% for the 24-h-ahead interval forecast in one of the best cases.
Peak demand alert system based on electricity demand forecasting for smart meter data
Komatsu, Hidenori (author) / Kimura, Osamu (author)
Energy and Buildings ; 225
2020-07-10
Article (Journal)
Electronic Resource
English
Electricity conservation , Information provision , Small- and medium-sized enterprises , Smart meter data , ANN , artificial neural networks , BEMS , building energy management system , JMA , Japan Meteorological Agency , MAPE , mean absolute percentage error , OLS , ordinary least squares , SII , sustainable open innovation initiative , SMEs , small- and medium-sized enterprises , SVR , support vector regression
Demand Management Smart meter model for electricity and water industry
Online Contents | 2010
Electricity Demand Forecasting Using Regression Techniques
| Springer Verlag | 2019
Electricity Demand Forecasting Using Regression Techniques
| TIBKAT | 2020