Deep Forest Regression for Short-Term Load Forecasting of Power Systems

Yin, Linfei; Sun, Zhixiang; Gao, Fang; Liu, Hui

doi:10.1109/access.2020.2979686

Cited by 56 publications

(18 citation statements)

References 56 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to DNNs, DF has fewer hyper-parameters, does not require backpropagation, is easy to train with low computational costs, and works well even for only small-scale training data. Since its inception, the DF algorithm 15 has demonstrated excellent performance in a wide range of applications in diverse fields such as diagnosing schizophrenia 17 , price prediction 18 , image retrieval 19 , drug interactions 20 , COVID-19 detection from CT images 21 , hyperspectral image classification 22 , human age estimation from face images 23 , short-term load forecasting of power systems 24 , and emotion recognition 25 among others.…”

Section: Introductionmentioning

confidence: 99%

Deep Forest Model for Diagnosing COVID-19 From Routine Blood Tests

AlJame

Imtiaz

Ahmad

et al. 2021

Preprint

View full text Add to dashboard Cite

The Coronavirus Disease 2019 (COVID-19) global pandemic has threatened the lives of people worldwide and poses considerable challenges. Early and accurate screening of infected people is vital for combating the disease. To help with the limited quantity of swab tests, we propose a machine learning prediction model to accurately diagnose COVID-19 from clinical and/or routine laboratory data. The model exploits a new ensemble-based method called the deep forest (DF), where multiple classifiers in multiple layers are used to encourage diversity and improve performance. The cascade level employs the layer-by-layer processing and is constructed from three different classifiers: extra trees, XGBoost, and LightGBM. The prediction model was trained and evaluated on two publicly available datasets. Experimental results show that the proposed DF model has an accuracy of 99.5%, sensitivity of 95.28%, and specificity of 99.96%. These performance metrics are comparable to other well-established machine learning techniques, and hence DF model can serve as a fast screening tool for COVID-19 patients at places where testing is scarce.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Forest Model for Diagnosing COVID-19 From Routine Blood Tests

AlJame

Imtiaz

Ahmad

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep neural network based approach is developed to model the heart failure of a patient with the use of ECG signals [ 19 ]. The Random forest model is also applicable to predict the heart failure of a patient [ 20 ].The forecasting of power systems have been done with the help of Random forest model [ 21 ]. The random forest algorithm provides an alternative approach to predict the uncertain data [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

Kalman filter based short term prediction model for COVID-19 spread

et al. 2020

View full text Add to dashboard Cite

Corona Virus Disease 2019 (COVID19) has emerged as a global medical emergency in the contemporary time. The spread scenario of this pandemic has shown many variations. Keeping all this in mind, this article is written after various studies and analysis on the latest data on COVID19 spread, which also includes the demographic and environmental factors. After gathering data from various resources, all data is integrated and passed into different Machine Learning Models in order to check its appropriateness. Ensemble Learning Technique, Random Forest, gives a good evaluation score on the tested data. Through this technique, various important factors are recognized and their contribution to the spread is analyzed. Also, linear relationships between various features are plotted through the heat map of Pearson Correlation matrix. Finally, Kalman Filter is used to estimate future spread of SARS-Cov-2, which shows good results on the tested data. The inferences from the Random Forest feature importance and Pearson Correlation gives many similarities and few dissimilarities, and these techniques successfully identify the different contributing factors. The Kalman Filter gives a satisfying result for short term estimation, but not so good performance for long term forecasting. Overall, the analysis, plots, inferences and forecast are satisfying and can help a lot in fighting the spread of the virus.

show abstract

“…In terms of the training set selection, there are two major methods: the horizontal training set selection method and the longitudinal training set selection method. The horizontal training set selection method is the most commonly used training set selection method, which selects continuous data samples from historical data as the training set [3], [4]. Reference [5] selects winter months as the training set when forecasting the daily peak load of January.…”

Section: Introductionmentioning

confidence: 99%

“…https://www.ema.gov.sg/statistic.aspx?sta_sid=20140826Y84sgBebjwKV4 https://aemo.com.au/en/energy-systems/electricity/national-electricitymarket-nem/data-nem/aggregated-data…”

mentioning

confidence: 99%

Short-Term Power Load Forecasting Based on Cross Multi-Model and Second Decision Mechanism

2020

View full text Add to dashboard Cite

Short-term load forecasting (STLF) plays a vital role in the reliable, secure, and efficient operation of power systems. Since electric load variation results from diverse factors, accurate and stable load forecasting remains a challenging task. To increase the forecasting accuracy and stability, in this paper, we newly propose a short-term load forecasting method based on the cross multi-model and second decision mechanism. First, we combine horizontal and longitudinal training set selection method to construct the cross training sets, which acquire both the horizontal and longitudinal characteristics of the load variation. Second, to improve the generalization ability and extend the application scope, we construct forecasting multi-models by training multiple forecasting algorithms with cross training sets. Finally, to aggregate the forecasting outputs obtained by the forecasting multi-models, we propose a second decision mechanism based on a decision multi-model and adaptive weight allocation strategy, which overcomes the limited learning ability shortcoming of single decision models and further improves the forecasting accuracy. Case studies based on electrical load data from the state of Maine, the region of New England, Singapore, and New South Wales of Australia show that both the accuracy and the stability of the proposed method are superior to the compared models. INDEX TERMS Short-term load forecasting, multi-model, cross training set, second decision mechanism, model aggregation

show abstract

Deep Forest Regression for Short-Term Load Forecasting of Power Systems

Cited by 56 publications

References 56 publications

Deep Forest Model for Diagnosing COVID-19 From Routine Blood Tests

Deep Forest Model for Diagnosing COVID-19 From Routine Blood Tests

Kalman filter based short term prediction model for COVID-19 spread

Short-Term Power Load Forecasting Based on Cross Multi-Model and Second Decision Mechanism

Contact Info

Product

Resources

About