Short-term wind speed forecasting based on two-stage preprocessing method, sparrow search algorithm and long short-term memory neural network

Ai, Xue-Yi; Li, Shijia; Xu, Haoxuan

doi:10.1016/j.egyr.2022.11.051

Cited by 18 publications

(12 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The techniques employed for calculating the proposed SASO‐based VPP TLC method are QEOIC (mD1), 16 ABC‐based TSC (mD2), 17 ROA‐based TSC (mD3), 18 BSO‐based TSC (mD4), 19 CSA‐based TSC (mD5), 20 mode search‐based TSC (mD6), and LSTM with SSA (mD7) 21 …”

Section: Resultsmentioning

confidence: 99%

Self‐adaptive search optimization‐based vehicle path prediction and traffic light controller in vehicular ad hoc network

Chauhan,

Kumar

2023

Int J Communication

View full text Add to dashboard Cite

SummaryIn recent days, VANET is considered as the main hopeful equipment in the system of transportation since traffic congestion arises regularly and thus occurred road accidents very easily. Besides, the network traffic is increasing due to the huge quantity of information generated in region of urban. Therefore, one of the primary challenges faced by Intelligent Transportation System (ITS) is ensuring the accurate transmission of information in both vehicle‐to‐vehicle (V2V) and vehicle‐to‐road (V2R) sensing unit communications. So, here, an adaptive routing controller (ARC) is utilized to improve the data transmission between vehicle and road sensing unit (RSU) and to minimize the traffic density in VANET, and the self‐adaptive search optimization is developed in VANET clustering to prioritize vehicles in the lane, in which the multi‐objective function is intended depending on the energy of the node, acceleration, jitter, priority, velocity, and trust factors. The traffic light control is done to facilitate the effective communication in the network. Thus, the proposed technique is calculated in terms of throughput, jitter, quadratic mean of acceleration (QMA), and spatially distributed travel time (SDTT), which acquired the values of 0.53 s, 36.07 kmph, 3.472 s, and 43.572%, respectively, while using 50 vehicles at 50 s.

show abstract

Section: Resultsmentioning

confidence: 99%

Self‐adaptive search optimization‐based vehicle path prediction and traffic light controller in vehicular ad hoc network

Chauhan,

Kumar

2023

Int J Communication

View full text Add to dashboard Cite

show abstract

“…Table 1 shows the benchmark test functions (Li and Wu, 2022). Table 2 shows the parameter settings of the algorithm (Catalao et al, 2011;Ai et al, 2022).…”

Section: Verification Of Itsamentioning

confidence: 99%

“…Still, due to their limited reserves, they are prone to serious environmental pollution during use and cannot meet the current world's demand for sustainable energy development (Liu S. et al, 2022;Zishan et al, 2023). Distributed power generation technology has emerged as an important way to alleviate energy shortages and environmental pollution issues (Ai et al, 2022;Mohale and Chelliah, 2022). Wind power generation, because of its pros of green, lowcarbon, and sustainable development, has become a more promising energy generation method (Zhu et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Wind power output prediction: a comparative study of extreme learning machine

Wang,

Niu

2023

Front. Energy Res.

View full text Add to dashboard Cite

This study aims to propose a wind power prediction method that achieves high accuracy in order to minimize the impact of wind power on the power system and reduce scheduling difficulties in systems incorporating wind power. The importance of developing renewable energy has been recognized by society due to the increasing severity of the energy crisis. Wind energy offers advantages such as efficiency, cleanliness, and ease of development. However, the random nature of wind energy poses challenges to power systems and complicates the scheduling process. Therefore, accurate wind power prediction is of utmost importance. A wind power prediction model was constructed based on an improved tunicate swarm algorithm–extreme learning machine (ITSA-ELM). The improved tunicate swarm algorithm (ITSA) optimizes the random parameters of extreme learning machine (ELM), resulting in the best prediction performance. ITSA is an enhancement of the tunicate swarm algorithm (TSA), which introduces a reverse learning mechanism, a non-linear self-learning factor, and a Cauchy mutation strategy to address the drawbacks of poor convergence and susceptibility to local optima in TSA. Two different scenarios were used to verify the effectiveness of ITSA-ELM. The results showed that ITSA-ELM has a decrease of 1.20% and 21.67% in MAPE, compared with TSA-ELM, in May and December, respectively. This study has significant implications for promoting the development of renewable energy and reducing scheduling difficulties in power systems.

show abstract

“…Such a strategy demonstrates its potentia to improve the forecasting performance of BiLSTM neural networks. SSA includes decomposition and reconstruction stages [36]. The decomposition stag includes two sub-processes of embedding and singular value decomposition.…”

Section: Singular Spectrum Analysismentioning

confidence: 99%

“…The singular value  denoises the original signal. Add SSA includes decomposition and reconstruction stages [36]. The decomposition stage includes two sub-processes of embedding and singular value decomposition.…”

Section: Singular Value Decompositionmentioning

confidence: 99%

Short-Term Photovoltaic Power Forecasting Based on Historical Information and Deep Learning Methods

Guo

Yan

2022

Sensors

View full text Add to dashboard Cite

The accurate prediction of photovoltaic (PV) power is essential for planning power systems and constructing intelligent grids. However, this has become difficult due to the intermittency and instability of PV power data. This paper introduces a deep learning framework based on 7.5 min-ahead and 15 min-ahead approaches to predict short-term PV power. Specifically, we propose a hybrid model based on singular spectrum analysis (SSA) and bidirectional long short-term memory (BiLSTM) networks with the Bayesian optimization (BO) algorithm. To begin, the SSA decomposes the PV power series into several sub-signals. Then, the BO algorithm automatically adjusts hyperparameters for the deep neural network architecture. Following that, parallel BiLSTM networks predict the value of each component. Finally, the prediction of the sub-signals is summed to generate the final prediction results. The performance of the proposed model is investigated using two datasets collected from real-world rooftop stations in eastern China. The 7.5 min-ahead predictions generated by the proposed model can reduce up to 380.51% error, and the 15 min-ahead predictions decrease by up to 296.01% error. The experimental results demonstrate the superiority of the proposed model in comparison to other forecasting methods.

show abstract

Short-term wind speed forecasting based on two-stage preprocessing method, sparrow search algorithm and long short-term memory neural network

Cited by 18 publications

References 42 publications

Self‐adaptive search optimization‐based vehicle path prediction and traffic light controller in vehicular ad hoc network

Self‐adaptive search optimization‐based vehicle path prediction and traffic light controller in vehicular ad hoc network

Wind power output prediction: a comparative study of extreme learning machine

Short-Term Photovoltaic Power Forecasting Based on Historical Information and Deep Learning Methods

Contact Info

Product

Resources

About