Journal
IET RENEWABLE POWER GENERATION
Volume 14, Issue 14, Pages 2657-2667Publisher
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-rpg.2019.1238
Keywords
wind power; probability; autoregressive processes; regression analysis; recurrent neural nets; power engineering computing; load forecasting; optimisation; intelligent optimisation techniques; model training; LSTM model; exogenous models; benchmarking models; real-world data sets; uncertain wind power forecasting; LSTM-based prediction interval; recurrent neural network; long short-term memory; power uncertainty forecast; nonparametric lower upper bound estimation framework; mutual information; false nearest neighbours techniques; nonlinear auto-regressive; reliable prediction intervals; typical RNN models; wind power data sets; variational synchronicity; comprehensive objective function
Ask authors/readers for more resources
Estimating prediction intervals (PIs) is an efficient and reliable way of capturing the uncertainties associated with wind power forecasting. In this study, a state of the art recurrent neural network (RNN) known as long short-term memory (LSTM) is used to produce reliable PIs for one-hour ahead wind power uncertainty forecast using the non-parametric lower upper bound estimation framework. Two realistic hourly stamped wind power data sets are obtained and by using mutual information and false nearest neighbours techniques, the data are made suitable for model inputs. A novel comprehensive objective function consisting of the coverage probability, the average width of the PIs, symmetricity and variational synchronicity is developed to train the LSTM model using intelligent optimisation techniques. The standard of the PIs generated for the test set as well as for different seasons are evaluated based on the indices used to design the objective function for model training, with one of them being modified. The performance of the proposed LSTM model is found to outperform typical RNN models like Elman, non-linear auto-regressive with exogenous models and other benchmarking models while tested on the real-world data sets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
Article
Green & Sustainable Science & Technology
An ultra-high voltage gain interleaved converter based on three-winding coupled inductor with reduced input current ripple for renewable energy applications
Seyed Majid Hashemzadeh, Mohammed A. Al-Hitmi, Hadi Aghaei, Vafa Marzang, Atif Iqbal, Ebrahim Babaei, Seyed Hossein Hosseini, Shirazul Islam
Summary: This article proposes an interleaved high step-up DC-DC converter topology with an ultra-high voltage conversion ratio for renewable energy applications. The converter utilizes an interleaved structure to reduce the input source current ripple, which is advantageous for solar PV sources. By employing voltage multiplier cells and coupled inductor techniques, the topology enhances the output voltage. The article provides comprehensive operation modes and steady-state analyses, compares the proposed structure with other similar converter topologies, and validates the mathematical analysis with experimental results.
IET RENEWABLE POWER GENERATION (2024)
Article
Green & Sustainable Science & Technology
Resilience enhancement of distribution networks based on demand response under extreme scenarios
Gang Xu, Zixuan Guo
Summary: This paper proposes a two-stage resilience enhancement strategy for the recovery of critical loads after disasters. The first stage utilizes a heuristic algorithm to determine the post-disaster topology, while the second stage incorporates user demand response to maximize the socio-economic value of the recovery.
IET RENEWABLE POWER GENERATION (2024)
Article
Green & Sustainable Science & Technology
Comparative analysis of different methods in estimating wind speed distribution, and evaluation of large-scale wind turbine performance in Rahva-Bitlis, Turkey
Faruk Oral
Summary: This study investigates the wind characteristics and electricity generation potential from wind energy in the Bitlis-Rahva region in eastern Turkey. Wind data from the Bitlis meteorological station is analyzed using the WindPRO program to determine the wind speed distribution and predict turbine performance. The results show that the region has low wind energy capacity factor, indicating it is not efficient for wind energy investments. However, it is suggested that higher altitudes in the region may have better wind energy utilization.
IET RENEWABLE POWER GENERATION (2024)
Article
Green & Sustainable Science & Technology
Design and control of modular multilevel matrix converter with symmetrically integrated energy storage for low frequency AC system
Yingjie Tang, Zheren Zhang, Zheng Xu
Summary: This paper investigates the modular multilevel matrix converter with symmetrically integrated energy storage for low frequency AC system. An evaluation method for the minimum required number of active submodules is presented, and the influences of operating conditions on the minimum required number of active submodules are studied. Issues about the converter control system are also discussed in this paper.
IET RENEWABLE POWER GENERATION (2024)