Model‐independent approach for short‐term electric load forecasting with guaranteed error convergence

Abstract

High precision short-term load forecasting is crucial for enhancing safe and effective operation of power systems. This study presents a new method for short-term load forecasting using the concept of trajectory tracking. Unlike most existing forecasting methods, the proposed one is essentially model independent in that the corresponding forecasting algorithms are derived without the need for the specific load models. Furthermore, based upon Lyapunov stability theory, the prediction error of the proposed method is shown to converge with sufficient accuracy one gives rise to better forecasting performance.Peer ReviewedPostprint (published version

Short Term Electrical Load Combination Forecasting Model based on Multi-dimensional Meteorological Information Spatio-Temporal Fusion and MPA-VMD

“…Least-Squares Support Vector Machine (LSSVM) is a better model obtained by optimizing on the Support Vector Machine (SVM) model to improve the convergence speed and the accuracy of the final prediction results during the iterative process [36][37][38]. However, the selection of parameters in the LSSVM model has a great impact on the performance of the model, so this paper proposes MPA to optimize the parameters of the LSSVM model [39]. The optimization model of LSSVM is as follows:…”

Short‐term electrical load forecasting model based on multi‐dimensional meteorological information spatio‐temporal fusion and optimized variational mode decomposition

“…Least‐Squares Support Vector Machine (LSSVM) is a better model obtained by optimizing the Support Vector Machine (SVM) model to improve the convergence speed and the accuracy of the final prediction results during the iterative process [36–38]. However, the selection of parameters in the LSSVM model has a great impact on the performance of the model, so this paper proposes MPA to optimize the parameters of the LSSVM model [39]. The optimization model of LSSVM is as follows: $$$$\begin{align} \underset{\omega ,\xi ,b}{\min}J(\omega ,\xi )=\frac{1}{2}{\omega}^{T}\omega +\frac{\gamma}{2}\sum _{i=1}^{N}{\xi}_{i}^{2}\nonumber\\ s.t.\ {y}_{i}={\omega}^{T}\varphi ({x}_{i})+b+{\xi}_{i},i=1,2,\text{\ensuremath{\ldots}},n \end{align}$$$$…”

“…Least-Squares Support Vector Machine (LSSVM) is a better model obtained by optimizing the Support Vector Machine (SVM) model to improve the convergence speed and the accuracy of the final prediction results during the iterative process [36][37][38]. However, the selection of parameters in the LSSVM model has a great impact on the performance of the model, so this paper proposes MPA to optimize the parameters of the LSSVM model [39]. The optimization model of LSSVM is as follows:…”

Power System Day-Ahead Unit Commitment Based on Chance-Constrained Dependent Chance Goal Programming

“…Due to the UC scheme needing to be made before observing the uncertain power supply and the actual power of the load, it is necessary to use various forecasting techniques to predict the output of the uncertain power supply of load in advance. Not only do wind speed, wind direction, temperature, turbine type, turbine position, terrain roughness, air density, and wake effect [40,41] combine to make it difficult to predict the output, but, at the same time, due to factors such as temperature, human social activities, and consumption behaviours [42][43][44], there are inevitable errors in load forecasts. The forecast error of load and an Elia-Connected wind power generator in Belgium in 2016 are shown in Figure 1.…”