Short term electric load forecasting using hybrid algorithm for smart cities
- PDF / 2,686,808 Bytes
- 21 Pages / 595.224 x 790.955 pts Page_size
- 18 Downloads / 222 Views
Short term electric load forecasting using hybrid algorithm for smart cities Ehab E. Elattar1,2 · Nehmdoh A. Sabiha1,2 · Mohammad Alsharef1 · Mohamed K. Metwaly1,2 · Amr M. Abd-Elhady2 · Ibrahim B. M. Taha1,3
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Many day-to-day operation decisions in a smart city need short term load forecasting (STLF) of its customers. STLF is a challenging task because the forecasting accuracy is affected by external factors whose relationships are usually complex and nonlinear. In this paper, a novel hybrid forecasting algorithm is proposed. The proposed hybrid forecasting method is based on locally weighted support vector regression (LWSVR) and the modified grasshopper optimization algorithm (MGOA). Obtaining the appropriate values of LWSVR parameters is vital to achieving satisfactory forecasting accuracy. Therefore, the MGOA is proposed in this paper to optimally select the LWSVR’s parameters. The proposed MGOA can be derived by presenting two modifications on the conventional GOA in which the chaotic initialization and the sigmoid decreasing criterion are employed to treat the drawbacks of the conventional GOA. Then the hybrid LWSVR-MGOA method is used to solve the STLF problem. The performance of the proposed LWSVR-MGOA method is assessed using six different realworld datasets. The results reveal that the proposed forecasting method gives a much better forecasting performance in comparison with some published forecasting methods in all cases. Keywords Smart cities · Short term load forecasting · Modified grasshopper optimization algorithm · Locally weighted support vector regression · Parameters optimization Nomenclature t {xi , yi }N i=1 Nt xi ∈ R n yi ∈ R Q(xi , x) = ϕ(xi ) · ϕ(x) ϕ(x) w b ζi , ζi∗
time series dataset number of training points input space of the dataset, i = 1, ..., Nt target value Gaussian kernel function high dimensional feature space vector contains the weight coefficients a real bias constant upper and lower training errors, respectively
Ehab E. Elattar
[email protected] 1
Electrical Engineering Department, College of Engineering, Taif University, Taif, 21974, Saudi Arabia
2
Electrical Engineering Department, Faculty of Engineering, Menoufia University, Shebin Elkom, 32511, Egypt
3
Electrical Engineering Department, Faculty of Engineering, Tanta University, Tanta, 31521, Egypt
C
ηi , ηi∗ xq K (1 < K Nt ) kmax Dk (xi )
Dmax ν Wi h
Ci Xi
regularization constant that determines the trade-off between upper and lower training errors and the flatness of function f Lagrange parameters the query point number of nearest neighbors the maximum number of nearest neighbors distance between each training point x and its nearest neighbors the maximum distance a constant number the weighting function bandwidth parameter which performs an essential role in local modelling weighted regularization constant position of the i th grasshopper
E. E. Elattar et al.
Si Gi Ai ng m U, L d T c1 , c2 it itmax cmax , cmin
u
n
Ai
Data Loading...
