Title :
A learnable kernel machine for short-term load forecasting
Author :
Zhang, Lin ; Dai, Guang ; Cao, Yijia ; Zhai, Guixiang ; Liu, Zhaoyan
Author_Institution :
Northwest China Grid Co. Ltd., Xi´´an
Abstract :
Short-term load forecasting is very important for decision making in power system operation and planning. During the last several years, kernel machines have been widely employed for short-term forecasting. Owing to the inherent limitations, the corresponding forecasting accuracy can be impaired. To overcome the limitations, this paper develops a novel kernel machine, hereafter called learnable kernel machine, for short-term load forecasting. The proposed method possesses several appealing properties. First, like all other kernel machines, it handles nonlinearity in a disciplined manner that is also computationally attractive; second, by incorporating both kernel learning and regularization parameter learning, it effectively enhances the overall performance; third, as the optimality criterion, it employs the leave-one-out error, leading to an almost unbiased estimator of the generalization error; forth, using the leave-one-out error as the optimality criterion, it can be also expressed in closed form, making it computationally feasible in practice; fifth, the computational cost to optimize the leave-one-out error can be further reduced by matrix technology. We present experimental results on real-world data sets to demonstrate the effectiveness.
Keywords :
learning (artificial intelligence); load forecasting; power system analysis computing; power system planning; decision making; learnable kernel machine; leave-one-out error; matrix technology; optimality criterion; power system operation; power system planning; regularization parameter learning; short-term load forecasting; Computational efficiency; Economic forecasting; Educational institutions; Kernel; Load forecasting; Machine learning; Neural networks; Power system planning; Power system reliability; Power systems;
Conference_Titel :
Power Systems Conference and Exposition, 2009. PSCE '09. IEEE/PES
Conference_Location :
Seattle, WA
Print_ISBN :
978-1-4244-3810-5
Electronic_ISBN :
978-1-4244-3811-2
DOI :
10.1109/PSCE.2009.4840015