Fast Univariate Time Series Prediction of Solar Power for Real-Time Control of Energy Storage System

Abstract

In this paper, super-short-term prediction of solar power generation for applications in dynamic control of energy system has been investigated. In order to follow and satisfy the dynamics of the controller, the deployed prediction method should have a fast response time. To this end, this paper proposes fast prediction methods to provide the control system with one step ahead of solar power generation. The proposed methods are based on univariate time series prediction. That is, instead of using external data such as the weather forecast as the input of prediction algorithms, they solely rely on past values of solar power data, hence lowering the volume and acquisition time of input data. In addition, the selected algorithms are able to generate the forecast output in less than a second. The proposed methods in this paper are grounded on four well-known prediction algorithms including Autoregressive Integrated Moving Average (ARIMA), K-Nearest Neighbors (kNN), Support Vector Regression (SVR), and Random Forest (RF). The speed and accuracy of the proposed algorithms have been compared based on two different error measures, Mean Absolute Error (MAE) and Symmetric Mean Absolute Percentage Error (SMAPE). Real world data collected from the PV installation at the University of California, Riverside (UCR) are used for prediction purposes. The results show that kNN and RF have better predicting performance with respect to SMAPE and MAE criteria.

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

“…However, sMAPE avoids all problems as suffered by MAPE [57,58]. Moreover, sMAPE is also extensively employed statistical measure for solar resource forecasting tasks [59]. The NSE [60] and d r [61] statistical measures also provide a meaningful comparison to assess the models performance.…”

Predicting the Future is Like Completing a Painting: Towards a Novel Method for Time-Series Forecasting

“…The processing and analysis of these times series data allows the development of context-aware applications and services in many applications domains, such as in e-health [43], transportation [44], and energy management [39]. For instance, short-term forecasting of solar power production and utility demand could allow dynamic and predictive control of micro-grid energy systems [45].…”

Peramalan Harga Telur Ayam Ras Di Jakarta Timur Berbasis Jaringan Syaraf Tiruan

“…Metode kedua relatif lebih efisien karena tidak memerlukan alat pengukuran lainnya selain dataset yang ada. Selain itu, untuk proses kontrol dinamis berkecepatan tinggi, yang memerlukan peramalan jangka pendek, metode univariat lebih efektif karena tidak bergantung pada proses akuisisi data yang berkepanjangan [10]. Penelitian yang memanfaatkan data univariat pun dapat menghasilkan akurasi yang cukup baik [11].…”

“…Penggunaan data univariat dapat menggunakan model linier (ARIMA dan Exponential Smoothing) ataupun model nonlinear (Jaringan Syaraf Tiruan, Support Vector Regression, Decision Tree, ataupun K-Nearest Neighboard). Model nonlinear dianggap lebih akurat dalam hal menangkap karakteristik nonlinear dan perilaku waktu yang bervariasi [10] [12].…”