scholarly journals A Hybrid Seasonal Mechanism with a Chaotic Cuckoo Search Algorithm with a Support Vector Regression Model for Electric Load Forecasting

Energies ◽  
2018 ◽  
Vol 11 (4) ◽  
pp. 1009 ◽  
Author(s):  
Yongquan Dong ◽  
Zichen Zhang ◽  
Wei-Chiang Hong
Keyword(s):  
Regression Model ◽  
Support Vector Regression ◽  
Search Algorithm ◽  
Load Forecasting ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Support Vector ◽  
Electric Load ◽  
Support Vector Regression Model ◽  
Electric Load Forecasting

scholarly journals Intelligent Fuzzy Logic - Cuckoo Search Algorithm Method for Short-Term Electric Load Forecasting in 150 kV Sulselrabar System

2017 ◽  
pp. 154 ◽  
Author(s):  
Muhammad Ruswandi Djalal ◽  
Faisal Faisal
Keyword(s):  
Fuzzy Logic ◽  
Search Algorithm ◽  
Load Forecasting ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Load Flow ◽  
Time Range ◽  
Electric Load ◽  
Short Term ◽  
Electric Load Forecasting

Forecasting the electrical load becomes important, because it can estimate electricity consumption over a certain time range. Accuracy in electric load forecasting can improve safety and reliability in the operation of power systems such as load flow, maintenance of generating units and scheduling of generating units. In this study used case study system Sulselrabar, which is currently growing, but still not much to discuss about the condition of the current system and which will come. Several methods for predicting electrical loads have been widely used, ranging from conventional to smart-based methods. In this research will be proposed method of artificial intelligence for forecasting Short Term load on Sulselrabar system. The method used is based Fuzzy Logic and Cuckoo Search Algorithm. The combination of Fuzzy logic and Cuckoo Search methods is chosen because the combination of both optimizes optimum fuzzy logic membership, so the forecasting results have a very small error. From the results of the research can be concluded that the result of load forecasting using Fuzzy Logic method optimized using Cuckoo Search Algorithm (FL-CSA) is better than Fuzzy Logic that is not optimized. The analysis results using input data 3 months before day H, to predict the load for one week on January 1 to 7 january 2014, and as a comparison used the predicted day H data. From the simulation results, the mean absolute percentage error (MAPE) is smaller using FLCSA, for the smallest MAPE on 1 January 2014 of 0.06785208%. While the highest MAPE on January 4, 2014 amounted to -0.44973%.

scholarly journals Dual-Mass MEMS Gyroscope Parallel Denoising and Temperature Compensation Processing Based on WLMP and CS-SVR

Micromachines ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 586 ◽  
Author(s):  
Longkang Chang ◽  
Huiliang Cao ◽  
Chong Shen
Keyword(s):  
Wavelet Transform ◽  
Support Vector Regression ◽  
Temperature Compensation ◽  
Linear Prediction ◽  
Search Algorithm ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Temperature Error ◽  
Support Vector ◽  
Mixed Features

For the sake of decreasing the effects of noise and temperature error on the measurement accuracy of micro-electro-mechanical system (MEMS) gyroscopes, a denoising and temperature drift compensation parallel model method based on wavelet transform and forward linear prediction (WFLP) and support vector regression based on the cuckoo search algorithm (CS-SVR) is proposed in this paper. First, variational mode decomposition (VMD) is proposed in this paper, which is aimed at dividing the output signal of the gyroscope into intrinsic mode functions (IMFs); then, the IMFs are classified into three features—drift, mixed, and pure noise features—by the sample entropy (SE) value. Second, a wavelet transform and forward linear prediction (WFLP) are combined to remove the noise from the mixed features. Meanwhile, the drift feature is compensated by support vector regression based on the cuckoo search algorithm (CS-SVR). Finally, through reconstruction, the final signal is obtained. Experimental results demonstrate that the VMD-SE-WFLP-CS-SVR method proposed in this paper can decrease noise and compensate the temperature error effectively (angular random walking value is optimized from 1.667°/√h to 0.0667°/√h and the bias stability is reduced from 30°/h to 4°/h). In terms of denoising, the performance of the WFLP algorithm is superior to the wavelet threshold and FLP, as it combines their advantages; furthermore, in terms of temperature compensation, the proposed CS-SVR algorithm uses the cuckoo search algorithm to find the optimal parameters of SVR, improving the accuracy of the model.

Sign in / Sign up

Export Citation Format

Share Document