1,668 Hits in 8.8 sec

Improving clustering based forecasting of aggregated distribution transformer loadings with gradient boosting and feature selection

George Rouwhorst, Mauricio Salazar, Phuong H. Nguyen, Han Slootweg
2021 IEEE Access  
Third, feature selection is applied to improve the forecast accuracy of each cluster. Finally, the day-ahead load forecast of all clusters are aggregated.  ...  Second, a gradient boosting algorithm is used to forecast the load of each cluster and calculate the related feature importance.  ...  FEATURE SELECTION As explained, (gradient) boosting algorithms based on DT have the advantage over other ML algorithms to interpret the correlation between the applied features and forecasted load based  ... 
doi:10.1109/access.2021.3137870 fatcat:4khxiegs3nfmlberwu6h6ozqvi

HSIC Bottleneck based Distributed Deep Learning Model for Load Forecasting in Smart Grid with A Comprehensive Survey

Md. Akhtaruzzaman, Mohammad Kamrul Hasan, S. Rayhan Kabir, Siti Norul Huda Sheikh Abdullah, Muhammad Jafar Sadeq, Eklas Hossain
2020 IEEE Access  
relevance and redundancy of feature selection in MTLF and improves the forecasting validity  ...  2) Feature extraction 3) Probability distribution Establishing LRD with CNN to improve the probability distribution based load forecasting and feature extraction  ...  CONFLICTS OF INTEREST The authors declare no conflict of interest.  ... 
doi:10.1109/access.2020.3040083 fatcat:tsqokovkm5gpfdsnm7bph73piu

Peak-Load Forecasting for Small Industries: A Machine Learning Approach

Dong-Hoon Kim, Eun-Kyu Lee, Naik Bakht Sania Qureshi
2020 Sustainability  
On the basis of the pattern of load information of most industrial facilities, new features were selected, and a generalized model was developed through the aggregation of ensemble models.  ...  Peak-load forecasting prevents energy waste and helps with environmental issues by establishing plans for the use of renewable energy. For that reason, the subject is still actively studied.  ...  Some studies evaluated special topics such as feature selection, feature extraction, similarity determination, and clustering that indirectly improve both time-series analysis and AI techniques, instead  ... 
doi:10.3390/su12166539 fatcat:znys4pj4frcjdcgh5jjwjw2uhe

Review of Low Voltage Load Forecasting: Methods, Applications, and Recommendations [article]

Stephen Haben, Siddharth Arora, Georgios Giasemidis, Marcus Voss, Danica Vukadinovic Greetham
2021 arXiv   pre-print
Reliable forecasting will be a necessary component of many of these systems to anticipate key features and uncertainties.  ...  Another aim of this paper is to facilitate the continued improvement and advancement in this area. To this end, the paper also surveys some of the most relevant and promising trends.  ...  Further, load profile clustering can be used to improve an aggregate forecast.  ... 
arXiv:2106.00006v2 fatcat:rb2yrt4tsjap3jhrb7dz76dg2e

Artificial Intelligence and Design of Experiments for Assessing Security of Electricity Supply: A Review and Strategic Outlook [article]

Jan Priesmann, Justin Münch, Elias Ridha, Thomas Spiegel, Marius Reich, Mario Adam, Lars Nolting, Aaron Praktiknjo
2021 arXiv   pre-print
Among other findings, we identify metamodeling of complex security of electricity supply models using AI methods and applications of AI-based methods for forecasts of storage dispatch and (non-)availabilities  ...  For this, we conduct a large-scale quantitative review on selected fields of application and methods and make a synthesis that relates the different disciplines to each other.  ...  Acknowledgements This research was funded by the German Federal Ministry for Economic Affairs and Energy (BMWi) within the project KIVi (grant ID:0 3EI1022A).  ... 
arXiv:2112.04889v2 fatcat:zfm7gfnfcraoplytbaixsdx2ia

Performance Evaluation of Distributed Machine Learning for Load Forecasting in Smart Grids

Dabeeruddin Syed, Shady S. Refaat, Haitham Abu-Rub
2020 2020 Cybernetics & Informatics (K&I)  
Load forecasting in smart grid is the process of predicting the amount of electrical power to meet the short, medium and long term demands.  ...  Using MLib allows testing the classic regression algorithms such as linear regression, generalized linear regression, decision tree, random forest and gradient-boosted trees in addition to survival regression  ...  In [4] , Dong et al. worked with the clustering of the load datasets based on the k-means clustering algorithm.  ... 
doi:10.1109/ki48306.2020.9039797 fatcat:qdjyvyfn75fwlgvxhj5i3wok3a

Short-Term Load Forecasting Based on the Transformer Model

Zezheng Zhao, Chunqiu Xia, Lian Chi, Xiaomin Chang, Wei Li, Ting Yang, Albert Y. Zomaya
2021 Information  
From the perspective of energy providers, accurate short-term load forecasting plays a significant role in the energy generation plan, efficient energy distribution process and electricity price strategy  ...  To handle these challenges, in this work, we introduce a novel model based on the Transformer network to provide an accurate day-ahead load forecasting service.  ...  We employed a novel boosting decision tree algorithm named light gradient boosting machine (LightGBM) to calculate the weight parameter and k-means cluster algorithm to deal with the similar day selection  ... 
doi:10.3390/info12120516 fatcat:ozypvifl7bco7dshz5c4yteaii

Day-Ahead Electric Load Forecasting for the Residential Building with a Small-Size Dataset Based on a Self-Organizing Map and a Stacking Ensemble Learning Method

Jaehyun Lee, Jinho Kim, Woong Ko
2019 Applied Sciences  
Recent increases in the adoption of advanced metering infrastructure (AMI) have made building electrical consumption data available, and this has increased the feasibility of data-driven load forecasting  ...  Using a clustering technique on small datasets could lead to overfitting when using forecasting models following an SOM network to be trained with clusters.  ...  This may include administrative and technical support, or donations in kind (e.g., materials used for experiments). Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app9061231 fatcat:72nxwuycnrccfkldpport4nuxa

Electrical peak demand forecasting- A review [article]

Shuang Dai, Fanlin Meng, Hongsheng Dai, Qian Wang, Xizhong Chen
2021 arXiv   pre-print
Thirdly, a comparative analysis of peak load forecast methods are summarized and different optimizing methods to improve the forecast performance are discussed.  ...  renewable energy at both transmission and distribution level, which characterizes the peak load demand with stronger randomness and less predictability and therefore poses a threat to the power grid security  ...  Commonly used boosting algorithms in the reviewed papers are adaptive boosting (AdaBoost), boosting tree, gradient boosting (GB) and Extreme gradient boosting (XGBoost).  ... 
arXiv:2108.01393v1 fatcat:2egx6ozkqzgvpfamdtpd6r2d4a

Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges

Yi Wang, Qixin Chen, Tao Hong, Chongqing Kang
2018 IEEE Transactions on Smart Grid  
Following the three stages of analytics, namely, descriptive, predictive and prescriptive analytics, we identify the key application areas as load analysis, load forecasting, and load management.  ...  How to employ massive smart meter data to promote and enhance the efficiency and sustainability of the power grid is a pressing issue.  ...  Combining the gradient boosting method and quantile regression, a boosting additive quantile regression method was proposed in [32] to quantify the uncertainty and generate probabilistic forecasts.  ... 
doi:10.1109/tsg.2018.2818167 fatcat:yacc5fol6vhydkw2azgy4mpfai

Multi-Timescale Forecasting of Battery Energy Storage State-of-Charge under Frequency Containment Reserve for Normal Operation

Aleksei Mashlakov, Samuli Honkapuro, Ville Tikka, Arto Kaarna, Lasse Lensu
2019 2019 16th International Conference on the European Energy Market (EEM)  
The battery state-of-charge data for the performance evaluation were simulated with a droop curve battery model based on the historical frequency data in the northern Europe synchronous area.  ...  Forecasting the state-of-charge changes of battery energy storage, anticipated from a provision of different services, can facilitate planning of its market participation strategy and leverage the maximum  ...  Light Gradient Boosting Machine Light Gradient Boosting Machine is a modern and fast gradient boosting framework that is also based on the DT algorithm [9] .  ... 
doi:10.1109/eem.2019.8916335 fatcat:w3ctsg6c7bhldbsbr2vnkc7fum

Guest Editorial for the Special Section on Advances in Renewable Energy Forecasting: Predictability, Business Models and Applications in the Power Industry

Ricardo J. Bessa, Pierre Pinson, George Kariniotakis, Dipti Srinivasan, Charlie Smith, Nima Amjady, Hamidreza Zareipour
2022 IEEE Transactions on Sustainable Energy  
They introduce a novel ensemble forecasting method based on model aggregation and feature engineering, adaptive error-based combination weights and forgetting factors.  ...  IMPROVE PREDICTABILITY WITH MODEL ENSEMBLE Nejati and Amjady present a model-agnostic hybrid classification-regression method for short-term point solar energy forecasting that i) uses a feature selecting  ... 
doi:10.1109/tste.2022.3157009 fatcat:opza5jppwbcb5ggbshlf72jqt4

An Ensemble Energy Consumption Forecasting Model Based on Spatial-Temporal Clustering Analysis in Residential Buildings

Anam-Nawaz Khan, Naeem Iqbal, Atif Rizwan, Rashid Ahmad, Do-Hyeun Kim
2021 Energies  
First, the apartment-level historical electric consumption data is clustered. Later the clusters are aggregated based on consumption profiles of consumers.  ...  The proposed ensemble forecasting scheme is well suited for predictive modeling and short-term load forecasting.  ...  Conflicts of Interest: The authors declare no conflict of interest regarding the publication of this paper.  ... 
doi:10.3390/en14113020 fatcat:a5bj4gvcvvb7vedq33giyzau3a

Guest Editorial: Advanced Data-Analytics for Power System Operation, Control and Enhanced Situational Awareness

2020 IET Generation, Transmission & Distribution  
The method sets the balance factor and modulating factor in the loss function of light gradient boosting machine (LightGBM).  ...  Lai, et al., in their paper 'Load forecasting based on deep neural network and historical data augmentation', present a load forecasting method known as deep neural network and historical data augmentation  ...  Her research interests include microgrid operation and planning, integration of distributed resources, data-driven energy storage system modelling, planning and control.  ... 
doi:10.1049/iet-gtd.2020.1493 fatcat:ern3em3movepzk6j33ohqlcndy

Forecasting Peak and Appliance Level Demand Using Smart Meter Data

R. Bhavya M., U. Vasuprada, Dr. Azra Nasreen
2021 Zenodo  
The hybrid MLP model with k-means clustering performs at accuracy in the range 84-99%.  ...  With this prediction, users can decide on the usage of appliances to manage electricity consumption and hence reduce the bill.  ...  Machine learning models like Extreme Gradient boosting (XGBoost), Categorical boosting, and light gradient boosting are applied on smart meter data to inspect the power theft problems which can cause a  ... 
doi:10.5281/zenodo.4925862 fatcat:gzmaulqz65bbnekpzsw3t6rc3a
« Previous Showing results 1 — 15 out of 1,668 results