Use of High-performance Graphics Processing Units for Power System Demand Forecasting

Abstract

-Load forecasting has always been essential to the operation and planning of power systems in deregulated electricity markets. Various methods have been proposed for load forecasting, and the neural network is one of the most widely accepted and used techniques. However, to obtain more accurate results, more information is needed as input variables, resulting in huge computational costs in the learning process. In this paper, to reduce training time in multi-layer perceptron-based short-term load forecasting, a graphics processing unit (GPU)-based computing method is introduced. The proposed approach is tested using the Korea electricity market historical demand data set. Results show that GPU-based computing greatly reduces computational costs.

A Review of Parallel Heterogeneous Computing Algorithms in Power Systems

“…The rest of the applications appear with less than five references with the use of GPU has been used (electrical vehicles [217][218][219][220], probabilistic power flow [221][222][223], power system visualization [232,233], electricity market [240], small signal analysis [241], transient stability-constrained optimal power flow [229], and short circuit analysis [234]).…”

“…GPU has helped with the following tasks: to optimize the large-scale design of electric vehicles [217], to accelerate probabilistic power flow computation based on the Monte-Carlo simulation with simple random sampling [223], to visualize real-time power system contouring based on a power grid digital elevation model [233], to forecast power system demand improving the data training of an artificial neural network with a multi-layer perceptron architecture using the Levenberg-Marquardt learning method [240], to approximate the solution of large differential-algebraic equations for small-signal stability with four methods (Chebyshev discretization, time integration operator discretization, linear multistep, and Padé approximants) [241], and to speed up the short-circuit current calculation of large-scale power systems with a batch solution where the admittance matrix inverse, short-circuit current of the specified node, node voltages, and branch currents are calculated in parallel with the SIMD technique [234].…”

Optimal Allocation of Energy Storage System for Risk Mitigation of DISCOs With High Renewable Penetrations

“…It is a basic task to support the decision of electricity procurement [24], [25] and can facilitate renewable penetrations [26], [27]. In this paper, a series of advanced forecast toolboxes [28] are used, including OptiLoad, OptiWind, and OptiSolar.…”

“…and can be normalized as (24), where is the global worst particle. All the five parameters are considered as fuzzy variables, and their values are assigned as membership grades in three fuzzy subsets: large (L), medium (M), and small (S): (24) Membership Functions: Gaussian curve membership function is chosen, whose definition is in the form of (25) For this ESS allocation problem, we determine parameters of the membership functions by experiments. is set t0 be the same for all membership functions.…”