Data-driven approaches show significant potential in accurately forecasting the power generation of wind turbines. However, it suffers from a lack of training data in various scenarios. Transfer learning has been employed as a solution to address the issue of limited data by leveraging data from other turbines. However, the conventional centralized training approach raises concerns about data privacy risks. In this study, we propose a privacy-preserving framework that incorporates federated learning and transfer learning for wind power forecasting. Firstly, we design a hybrid model with a series architecture as the backbone model to improve forecasting accuracy. Secondly, the proposed two-stage framework consists of federated learning-based pre-training and personalized fine-tuning. The federated learning stage pre-trains a knowledge-sharing model without disclosing raw data from source domains. Based on the pre-trained global model, personalized fine-tuning is applied to establish a customized model for the target turbine. Experimental results demonstrate that the proposed hybrid model achieves better forecasting accuracy. Additionally, the two-stage framework not only addresses insufficient data while considering privacy preservation but also enhances personalized adaptation of shared knowledge for the target turbine. Compared to local training and traditional federated learning, the proposed framework demonstrates obvious accuracy improvements, reaching up to 43.32 % and 27.94 %, respectively. 

A privacy-preserving framework integrating federated learning and transfer learning for wind power forecasting

Accurate load forecasting plays an important role in promoting low-carbon energy and high-quality utilization of electricity, as well as carbon reduction and safety in energy and power systems. The complexity of power system trends leads to widespread uncertainty in load forecasting. This article analyzes the internal mechanisms of load and meteorological factors at the level of multidimensional uncertainty and proposes a bidirectional memory feature hybrid model based on a new intelligent optimization method. The VMD optimized by gray wolf decomposes the electricity load data into different information modal components. The decomposed components are statistically analyzed with multidimensional uncertainty analysis to extract statistical patterns. The GTO part is optimized according to the fitness value to update the population and global optimal solution. Furthermore, convolutional neural networks (CNN) are used to extract potential features from load and meteorological data and enhance the correlation between input and output data. Then, short-term load forecasting is realized by using bi-directional short-term memory neural network (BiLSTM). The results show that the proposed model has smaller errors than several commonly used models, and has higher prediction accuracy. It can provide some new ideas for relevant departments to carry out power economic dispatch work in low-carbon modes. 

A new intelligent hybrid forecasting method for power load considering uncertainty

Accurate wind speed prediction is crucial for enhancing the stability and economic efficiency of power system operation, particularly in wind power grid integration. However, existing methods face challenges as they fail to explicitly model local and long-range spatial correlations simultaneously, thereby limiting the performance of wind speed prediction to a certain extent. To overcome these challenges, this study develops a novel method, namely, LLConvLSTM, from the perspective of modeling local and long-range spatial correlations in wind speed, which leverages Deformable Convolution V2 and Coordinate Attention for multi-step spatiotemporal wind speed prediction. A ConvLSTM encoder–decoder architecture is designed for end-to-end spatiotemporal wind speed prediction. The Residual Deformable Convolution Module (RDCM) increases additional offsets and modulation scales in the spatial sampling locations, enhancing the capability to capture local spatial correlations. Dense Coordinate Attention Module (DCAM) embeds spatial positional information into the channel attention. DCAM improves the representability of long-range spatial correlations. Experimental results based on wind speed data from 253 virtual wind turbines demonstrate that the proposed approach significantly outperforms existing methods throughout the entire year and months. Moreover, the proposed method achieves Mean Squared Error (MSE) of 0.1199, 0.3446 and 0.5798 for multi-step wind speed prediction, representing reductions of 22.47% to 40.91% compared with existing methods. These findings highlight the significance of modeling local and long-range spatial correlations in enhancing the accuracy and stability of wind speed prediction. Future research will design a universal method capable of handling turbine data from any location and emphasize long-term forecasting in wind speed prediction. 

Local and Long-range Convolutional LSTM Network: A novel multi-step wind speed prediction approach for modeling local and long-range spatial correlations based on ConvLSTM

A novel ultra-short-term wind power forecasting method based on TCN and Informer models

Improving wind speed prediction is essential for increasing the use of wind energy and promoting sustainable utilization of resources. Most previous studies relied on single-valued data with a common frequency, resulting in limited wind energy utilization. To fill this research gap and strengthen the precision of wind speed prediction, this study proposes a new multi-objective ensemble forecasting system based on a mixed-frequency interval-valued modeling paradigm for power system decision-making. The system comprises three modules: interval-valued data preprocessing module, mixed-frequency interval-valued forecasting module, and multi-objective ensemble module. Firstly, to reduce the data complexity by preprocessing the mixed-frequency interval-valued wind speed data, an interval-valued data preprocessing module is designed. Then, different types of prediction models, including a mixed data sampling model, two artificial intelligence models, and a traditional statistical model, are used to predict each subsequence in the mixed-frequency interval-valued forecasting module. Finally, a multi-objective ensemble module is designed to ensemble the interval-valued prediction results of each sub-model, and the final interval-valued wind speed forecast results are obtained. The proposed system obtained IMAE values of 0.4634 and 0.3452 at sites from Inner Mongolia and Penglai, China, respectively; this provides a significant tool for wind speed prediction. 

A new multi-objective ensemble wind speed forecasting system: Mixed-frequency interval-valued modeling paradigm

Gray wolf optimization-based wind power load mid-long term forecasting algorithm

With the advancement of the economy, the issue of energy supply and pollution has grown increasingly critical. Electric Vehicles (EVs) and innovative energy sources are progressively gaining popularity as a means of reducing the environmental damage caused by societal development. Photovoltaic charging stations can help integrate renewable energy and electric automobiles, and they have a promising future. This paper proposes a reservation charging model based on EV owners' willingness from the perspective of aggregator profitability and reducing the load peak-to-valley difference, as well as pre-consumption of PV for real-time charging EVs without advance reservation, which reduces the negative impact of direct PV access to the distribution network. The model is independent of PV power generation and EV charging data predictions, and it provides a theoretical foundation for how PV charging stations can achieve orderly charging management for EVs according to the peak-valley tariff and grid load characteristics. It can effectively reduce the load peak-valley difference and improve aggregators' net profit through the analysis of calculation cases.

Research on an Orderly Charging Strategy for New Energy Charging Stations Based on Dynamic Electricity Prices and a Reservation Charging Mechanism for Electric Vehicles

Multi-area transmission maintenance scheduling for two-level markets

With the advancement of market-oriented reform, the demand side has been gradually becoming an effective measure to ensure the security of power grid. In above transitional stage, a loss model of planned outage needs to be constructed to make decisions together with demand side management measures. In order to coordinate safety and economy, strengthen the analysis of the impact of new energy uncertainty on power grid operation, this paper is aimed to building an optimal decision-making method for planned outage and demand side management. Based on the confidence interval of new energy prediction, this method establishes a comprehensive optimization model considering both day-ahead and real-time time scales, and solves the optimal combination scheme of day-ahead orderly power utilization, day ahead schedulable load, temporary power restriction and real-time interruptible load under a certain degree of confidence. This paper further searches and adjusts the degree of confidence in which the confidence interval of new energy prediction is made, and studies the global optimal decision-making scheme. Finally, an example is given to prove the effectiveness and feasibility of the optimal decision-making method.

The Optimal Decision-Making Method of Planned Outage and Demand Side Management Based on The Confidence Interval of New Energy Prediction

Rolling Smooth Control Method for Renewable Energy Output with Supporting Energy Storage Considered

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yuxuan Li

Author Tools

Chat about Author