A Data Science Approach to Modelling a Manufacturing Facility's Electrical Energy Profile from Plant Production Data

Mulrennan, Konrad; Donovan, John J.; Tormey, David; Macpherson, Russell

doi:10.1109/dsaa.2018.00050

Cited by 9 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the setup of the Random Forest it is an efficient non-linear technique that avoids over-fitting [11]. It also shows transparency as a tuning parameter manages the amount of input features in each node by selecting when to divide the input data to create a new classifier [12]. Training multiple trees allows an overall ranking of feature importance which improves in accuracy as more trees are included in the Random Forest [13].…”

Section: Modelling Methodologymentioning

confidence: 99%

Technical Indicators and Prediction for Energy Market Forecasting

McHugh

Coleman

Kerr

2020

2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Machine learning usage for forecasting is popular in financial trading, particularly for stock price prediction and this is often combined with technical indicators to extract key predictive indicators from large time series trading datasets. Energy market trading data have similar characteristics to financial trading data, therefore deriving technical indicators specifically for electricity prices will help predict future prices and reduce trading costs. We have derived eight technical indicators for the Integrated Single Electricity Market (ISEM) energy market in Ireland using hourly electricity price data over the period February 2019 until November 2019. Technical indicator based models were obtained by using machine learning regression algorithms (Extreme Gradient [XG] Boost, Random Forest, and Gradient Boosting) trained with the proposed novel technical indicators. The results of the technical indicator models were compared against the baseline model (raw price data only) to see if using technical indicators as inputs improves model performance. We conclude that electricity prices can be accurately predicted using the proposed technical indicators.

show abstract

Section: Modelling Methodologymentioning

confidence: 99%

Technical Indicators and Prediction for Energy Market Forecasting

McHugh

Coleman

Kerr

2020

2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

show abstract

“…Moreover, the TIRS gathers the data in two long wavelength thermal infrared bands which are bands 10 and 11 that have a resolution of 100m and are resampled to 30m during delivery of the data product. generally dividing the testing points using the 75:25 ratio provides very good accuracy [27]. Hence, 12 stations were chosen to perform the study, which is around 75% of the existing available stations, and the other four stations were used to test the validity of the established model.…”

Section: Data Acquisitionmentioning

confidence: 99%

Particulate matter (pm10) monitoring in the United Arab Emirates using a satellite remote sensing based model

Suwaidi,

Ali,

Atabay

et al. 2023

Preprint

View full text Add to dashboard Cite

Particulate matter (PM) is one of the major factors causing air pollution, which is considered a concern for human health. Hence, measuring and monitoring the concentrations of these particles is essential. In this study, the main objective is to develop a remote sensing based PM10 monitoring model for the United Arab Emirates (UAE) using Landsat 8 imagery. Landsat 8 images acquired during the four-year period from 2016–2020 were obtained and used along with PM10 data collected at 16 ground monitoring stations corresponding to the acquisition of the satellite data. The Landsat 8 data was obtained from the United States Geological Survey (USGS) Core Science Systems in the form of Digital Numbers (DNs). The DNs of the four optical bands of Landsat 8 were then converted to top of the atmosphere reflectance (TOA) through radiometric processing, and then used to estimate the Aerosol Optical Thickness. A spectral PM10 model was then developed through regression analysis, correlating AOT to PM10 values obtained at the ground stations. The model provided an R-squared value of 62% and a Root Mean Square Error (RMSE) of 17.67 µg/m3. The results suggest that the developed model is robust in estimating PM10 values and can therefore be used for satellite-based monitoring at any location in the UAE.

show abstract