Medium and long-term wind energy forecasting method considering multi-scale periodic pattern

Lin, Yisha; Lu, Zongxiang; Qiao, Ying; Li, Mingjie; Liang, Zhifeng

doi:10.1051/e3sconf/202018201002

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The wavelet-based periodic pattern is used, and the conditional probability distribution given class is deployed. Periodic pattern recognition and class forecasting are conducted based on the same steps in [16]. The empirical distribution of each class based on historical data is used as the conditional probability distribution.…”

Section: Estimation On ô𝛿mentioning

confidence: 99%

Long‐term generation scheduling for renewable‐dominant systems concerning limited energy supporting capability of hydrogeneration

Lin

Qiao

2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

Renewable-dominant mixtures with hydrogeneration and variable renewable energies (VREs) have been the focus for decarbonization of power systems. Hydrogeneration with large reservoir becomes the main regulating source. The long-term generation scheduling (LTGS) on monthly reservoir regulation for the approaching year becomes more significant because reserving adequate water storage is related to intramonth balance, considering that hydrogeneration has to supplement deficit energy of VRE generation. However, conventional LTGS method that is based on monthly averages overestimates the hydrogeneration's intramonth energy supporting capability, whereas rolling short-term generation scheduling method cannot account the long-term effect of reservoir regulation decisions. This paper proposes a new LTGS method accounting intramonth imbalance risk that the energy deficit of VRE generation exceeds the maximum supporting energy of hydrogeneration. Since intramonth imbalance risk is coupled with LTGS in an uncertain and implicit way, intramonth extreme scenarios are introduced based on distribution quantiles of natural inflow of reservoirs and VRE generation, and the probabilistic intramonth imbalance risk constraints can be transformed as the hydrogeneration must supplement energy deficit of VRE generation during the extreme scenarios. A case study is conducted on a Wind-PV-Hydro energy base of southwestern China. The proposed method is found able to improve the feasibility and reliability of LTGS compared to other LTGS methods. Moreover, the high calculation efficiency of conventional LTGS method is inherited.

show abstract

Section: Estimation On ô𝛿mentioning

confidence: 99%

Long‐term generation scheduling for renewable‐dominant systems concerning limited energy supporting capability of hydrogeneration

Lin

Qiao

2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, there have been numerous studies on power demand forecasting methods. References [3][4][5] propose various forecasting methods considering factors such as economic development, temperature changes, and population growth. However, most of these methods focus on the next 10-15 years and do not capture the characteristics of the dual carbon goals.…”

Section: Introductionmentioning

confidence: 99%

Study on the development of electricity demand forecasting system under the carbon neutral goal

Li,

Wu,

Huang

et al. 2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

The goal of carbon peaking and carbon neutrality will accelerate the transformation of all walks of life in the whole society, especially the energy system. As the power industry is an energy hub, the energy sector will have a nonnegligible impact on power demand in the process. To this end, this paper is based on analyzing the impact of the carbon peaking and carbon neutrality target on energy and power, excavating the correlation between carbon and electricity demand, proposes an analysis of the development trend of different industries and construct electricity forecasting method system under the carbon neutrality target; taking East China as a typical case, studies the development trend of medium and long-term electricity demand in East China. The research results show that the analysis ideas and scheme system constructed are scientific and feasible, the prediction conclusions are reasonable, and have a good foresight.

show abstract

“…2) Data-driven means using artificial intelligence algorithms such as regression analysis, neural network analysis, and deep learning to achieve short-term forecasting based on historical data or longterm forecasting based on trends. For example, in literature [7], different time scales of data are integrated as input features for stacked long short-term memory neural network models. This approach fully considers the interdependencies of data from different time scales, effectively enhancing the accuracy of medium and longterm system-level load predictions.In literature [8], convolutional neural networks are employed for feature fusion, combined with long short-term memory neural networks to perform short-term predictions for regional loads.…”

Section: Introductionmentioning

confidence: 99%

EV Charging Load Forecasting Based on Model Driven and Data Driven

Tai,

Chen,

Wang

et al. 2024

Preprint

View full text Add to dashboard Cite

Based on the integration of dynamic traffic information, environmental temperature, real-time traffic flow, queuing theory, and other methods, a novel deep learning architecture for predicting Origin-Destination traffic flow in urban transportation systems has been developed to forecast the spatial and temporal distribution of electric vehicle charging loads.This method begins by analyzing the impact of various factors, such as urban traffic network data, daily patterns, and weather, on the driving patterns of electric vehicles. It employs a Graph Convolutional Recursive Neural Network algorithm to separately identify the starting and ending points of private cars and taxis.Next, it introduces impedance models for road segments and nodes, which take into account dynamic traffic information, intersection flow, and an air conditioning energy consumption model that considers environmental temperature and real-time vehicle speed. The method utilizes Graph Convolutional Network to extract spatial features of traffic nodes and their neighboring nodes. Time-related features are extracted using P-Prophet, creating a traffic intersection traffic flow prediction model.To optimize the minimum cost travel routes for electric vehicles, it improves the Floyd dynamic algorithm using a sparse graph optimization strategy, thereby simulating the driving behavior of electric vehicle users. Additionally, it uses K-means clustering to analyze potential charging preferences of electric vehicle users, providing insights into characteristic charging behaviors among typical urban electric vehicle users.

show abstract

Medium and long-term wind energy forecasting method considering multi-scale periodic pattern

Cited by 4 publications

References 11 publications

Long‐term generation scheduling for renewable‐dominant systems concerning limited energy supporting capability of hydrogeneration

Long‐term generation scheduling for renewable‐dominant systems concerning limited energy supporting capability of hydrogeneration

Study on the development of electricity demand forecasting system under the carbon neutral goal

EV Charging Load Forecasting Based on Model Driven and Data Driven

Contact Info

Product

Resources

About