A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation

2021 ◽  
pp. 103481
Author(s):  
Yue Li ◽  
Zheming Tong ◽  
Shuiguang Tong ◽  
Dane Westerdahl
Keyword(s):  
Building Energy ◽  
Data Driven ◽  
Forecasting Model ◽  
Fuzzy Information ◽  
Information Granulation ◽  
Energy Prediction ◽  
Fuzzy Information Granulation

A data-driven fuzzy information granulation approach for battery state of health forecasting

2020 ◽  
Vol 475 ◽  
pp. 228716 ◽  
Author(s):  
Wenjie Pan ◽  
Qi Chen ◽  
Maotao Zhu ◽  
Jie Tang ◽  
Jianling Wang
Keyword(s):  
Data Driven ◽  
State Of Health ◽  
Fuzzy Information ◽  
Information Granulation ◽  
Fuzzy Information Granulation

scholarly journals A Novel Agricultural Commodity Price Forecasting Model Based on Fuzzy Information Granulation and MEA-SVM Model

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Yongli Zhang ◽  
Sanggyun Na
Keyword(s):  
Price Index ◽  
Commodity Price ◽  
Series Data ◽  
Forecasting Model ◽  
Price Forecasting ◽  
Fuzzy Information ◽  
Agricultural Commodity ◽  
Information Granulation ◽  
Svm Model ◽  
Fuzzy Information Granulation

Accurately predicting the price of agricultural commodity is very important for evading market risk, increasing agricultural income, and accomplishing government macroeconomic regulation. With the price index predictions of 6 commodities of Food and Agriculture Organization of the United Nations (FAO) as examples, this paper proposed a novel agricultural commodity price forecasting model which combined the fuzzy information granulation, mind evolutionary algorithm (MEA), and support vector machine (SVM). Firstly, the time series data of agricultural commodity price index was transformed into fuzzy information granulation particles made up ofLow,R, andUp, which represented the trend and magnitude of price movement. Secondly, MEA algorithm was employed to seek the optimal parameterscandgfor SVM to establish the MEA-SVM model. Finally, FOA price index fluctuation range and change trend in the future were predicted by the MEA-SVM model. The empirical analysis showed that the MEA-SVM model was effective and had higher prediction accuracy and faster calculation speed in the forecasting of agricultural commodity price.

scholarly journals Predicting Building Energy Consumption using Engineering and Data Driven Approaches: A Review

2017 ◽  
Vol 2 (5) ◽  
pp. 44 ◽  
Author(s):  
Aulon Shabani ◽  
Orion Zavalani
Keyword(s):  
Energy Consumption ◽  
Energy Management ◽  
Building Energy ◽  
Data Driven ◽  
World Population ◽  
Design Phase ◽  
Energy Prediction ◽  
Important Concern ◽  
Paper Review ◽  
Second Category

Rapid growth of world population has higher impact on increasing buildings energy consumption. Therefore, improving energy consumption is an important concern for building engineers and operators. Energy management through forecasting approaches as one of most effective methods is in focus of this paper. Review of most elaborated methods is in our focus, where we investigate two main directions of energy prediction approaches. First category of approaches focuses on engineering methods mainly very reliable on building early operation stages and design phase, meanwhile second category go through data driven methods. Existing research works focused on these two models are introduced emphasizing advantages and relevant applications of methods.

Short-Term Wind Speed and Power Prediction Using Fuzzy Information Granulation-Support Vector Machine

2012 ◽  
Vol 608-609 ◽  
pp. 814-817
Author(s):  
Xiao Fu ◽  
Dong Xiang Jiang
Keyword(s):  
Support Vector Machine ◽  
Wind Speed ◽  
Wind Farm ◽  
Support Vector ◽  
Fuzzy Information ◽  
Short Term ◽  
Power Fluctuation ◽  
Data Set ◽  
Information Granulation ◽  
Fuzzy Information Granulation

The power fluctuation of wind turbine often causes serious problems in electricity grids. Therefore, short term prediction of wind speed and power as to eliminate the uncertainty determined crucially the development of wind energy. Compared with physical methods, support vector machine (SVM) as an intelligent artificial method is more general and shows better nonlinear modeling capacity. A model which combined fuzzy information granulation with SVM method was developed and implemented in short term future trend prediction of wind speed and power. The data, including the daily wind speed and power, from a wind farm in northern China were used to evaluate the proposed method. The prediction results show that the proposed model performs better and more stable than the standard SVM model when apply them into the same data set.

Sign in / Sign up

Export Citation Format

Share Document