☆ 4.7 Article

Short-term district power load self-prediction based on improved XGBoost model

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Energy & Fuels

Power Load Forecasting Considering Climate Factors Based on IPSO-Elman Method in China

Jicheng Liu et al.

Summary: This study aims to construct a load prediction model considering climate factors based on historical data and prove that prediction accuracy is related to climate factors and load regularity. By screening climate variables, a load prediction model based on the IPSO-Elman network learning algorithm is constructed. The particle swarm optimization algorithm is used to optimize parameters to improve the prediction accuracy of the Elman neural network. Prediction with and without climate factors is compared and analyzed, and the prediction accuracy of the model is evaluated using various indicators. The stability discriminant index of historical load regularity is introduced to prove the relationship between prediction accuracy and load regularity.

ENERGIES (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An adaptive backpropagation algorithm for long-term electricity load forecasting

Nooriya A. Mohammed et al.

Summary: This study introduces an improved ANN model with an Adaptive Backpropagation Algorithm (ABPA) for forecasting long-term electricity load demand, adjusting forecast values to account for behavioral differences between training and future datasets.

NEURAL COMPUTING & APPLICATIONS (2022)

添加到收藏夹

Article Energy & Fuels

Scenario prediction for power loads using a pixel convolutional neural network and an optimization strategy

Wenlong Liao et al.

Summary: This paper proposes a new deep generative network-based method for scenario prediction of power loads, which generates a group of possible power load scenarios to model stochastic behavior and outperforms other generative networks.

ENERGY REPORTS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost

Xiaotong Yao et al.

Summary: This study proposes a short-term power load forecasting model based on feature selection and error correction. By selecting key features and correcting errors using predicted values, the accuracy and reliability of the predictions are improved.

IEEE ACCESS (2022)

添加到收藏夹

Article Energy & Fuels

Short-term apartment-level load forecasting using a modified neural network with selected auto-regressive features

Lechen Li et al.

Summary: This study develops a neural network model based on Convolutional Long Short-Term Memory, employing autoregressive features selection, exogenous features selection, and a default state to improve short-term residential electricity load forecasting accuracy. The model demonstrates up to 25% accuracy improvement in forecasting load across three spatial granularities in a multi-family residential building.

APPLIED ENERGY (2021)

添加到收藏夹

Article Energy & Fuels

Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization

Xue-Bo Jin et al.

Summary: Short-term electrical load forecasting is essential for power system management, and this paper proposed an attention-based encoder-decoder network with Bayesian optimization for accurate predictions. The model outperformed others in terms of prediction accuracy and algorithm stability, providing an effective approach for time-series power load prediction with deep-learning technology.

ENERGIES (2021)

添加到收藏夹

Article Energy & Fuels

N-BEATS neural network for mid-term electricity load forecasting

Boris N. Oreshkin et al.

Summary: The proposed deep neural network modeling approach effectively solves the mid-term electricity load forecasting problem, outperforming all competitors in terms of both accuracy and forecast bias. It is simple to implement, does not require signal preprocessing, and is equipped with a forecast bias reduction mechanism.

APPLIED ENERGY (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids

Sheraz Aslam et al.

Summary: Microgrids combining renewable energy sources, energy storage devices, and load management methods face challenges due to the intermittent nature of renewables. Forecasting power generation from renewables is crucial for efficient grid operations and optimal resource utilization. Machine learning and deep learning models show promise in predicting energy demand and generation, with the efficiency of forecasting methods depending on historical data availability.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Smart Home Energy Management: Sequence-to-Sequence Load Forecasting and Q-Learning

Mina Razghandi et al.

Summary: In this paper, a Seq2Seq learning-based energy management system (HEMS) control method is proposed, which predicts supply and load conditions, optimizes offline using Q-learning, and tests online performance with actual data. The research results show that Seq2Seq learning performs better in both prediction and operation levels.

2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) (2021)

添加到收藏夹

Proceedings Paper Telecommunications

Short-Term Load Forecasting for Smart Home Appliances with Sequence to Sequence Learning

Mina Razghandi et al.

Summary: The study introduces an LSTM-based sequence-to-sequence model for appliance-level load forecasting, which outperforms other techniques in terms of prediction error based on experiments conducted on real datasets from residential buildings.

IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021) (2021)

添加到收藏夹

Article Energy & Fuels

Dual Deep Learning Networks Based Load Forecasting with Partial Real-Time Information and Its Application to System Marginal Price Prediction

Khikmafaris Yudantaka et al.

ENERGIES (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

An ensemble method of full wavelet packet transform and neural network for short term electrical load forecasting

Mohamed El-Hendawi et al.

ELECTRIC POWER SYSTEMS RESEARCH (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

Xu Xu et al.

IEEE TRANSACTIONS ON SMART GRID (2020)

添加到收藏夹

Review Energy & Fuels

Intelligent Systems for Power Load Forecasting: A Study Review

Ibrahim Salem Jahan et al.

ENERGIES (2020)

添加到收藏夹

Article Computer Science, Information Systems

Reactive Load Prediction Based on a Long Short-Term Memory Neural Network

Xu Zhang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Thermodynamics

Predicting residential energy consumption using CNN-LSTM neural networks

Tae-Young Kim et al.

ENERGY (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

Prediction Interval Adjustment for Load-Forecasting using Machine Learning

Miguel A. Zuniga-Garcia et al.

APPLIED SCIENCES-BASEL (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Short-Term Residential Load Forecasting Based on Resident Behaviour Learning

Weicong Kong et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

An electrical load measurements dataset of United Kingdom households from a two-year longitudinal study

David Murray et al.

SCIENTIFIC DATA (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Pattern-based local linear regression models for short-term load forecasting

Grzegorz Dudek

ELECTRIC POWER SYSTEMS RESEARCH (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

Forecasting electricity load by a novel recurrent extreme learning machines approach

Omer Faruk Ertugrul

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2016)

添加到收藏夹

Article Multidisciplinary Sciences

The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes

Jack Kelly et al.

SCIENTIFIC DATA (2015)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.