Monitoring, Predicting, and Optimizing Energy Consumptions

Research Anthology on Clean Energy Management and Solutions ◽

10.4018/978-1-7998-9152-9.ch002 ◽

2021 ◽

pp. 20-47

Author(s):

Pedro J. S. Cardoso ◽

Jânio Monteiro ◽

Cristiano Cabrita ◽

Jorge Semião ◽

Dario Medina Cruz ◽

...

Keyword(s):

Machine Learning ◽

Energy Consumption ◽

Optimization Algorithms ◽

Smart System ◽

Effective Reduction ◽

Energy Consumptions

Energy consumption and, consequently, the associated costs (e.g., environmental and monetary) concern most individuals, companies, and institutions. Platforms for the monitoring, predicting, and optimizing energy consumption are an important asset that can contribute to the awareness about the ongoing usage levels, but also to an effective reduction of these levels. A solution is to leave the decisions to smart system, supported for instance in machine learning and optimization algorithms. This chapter involves those aspects and the related fields with emphasis in the prediction of energy consumption to optimize its usage policies.

Download Full-text

Monitoring, Predicting, and Optimizing Energy Consumptions

Smart Systems Design, Applications, and Challenges - Advances in Computational Intelligence and Robotics ◽

10.4018/978-1-7998-2112-0.ch005 ◽

2020 ◽

pp. 80-107

Author(s):

Pedro J. S. Cardoso ◽

Jânio Monteiro ◽

Cristiano Cabrita ◽

Jorge Semião ◽

Dario Medina Cruz ◽

...

Keyword(s):

Machine Learning ◽

Energy Consumption ◽

Optimization Algorithms ◽

Smart System ◽

Effective Reduction ◽

Energy Consumptions

Energy consumption and, consequently, the associated costs (e.g., environmental and monetary) concern most individuals, companies, and institutions. Platforms for the monitoring, predicting, and optimizing energy consumption are an important asset that can contribute to the awareness about the ongoing usage levels, but also to an effective reduction of these levels. A solution is to leave the decisions to smart system, supported for instance in machine learning and optimization algorithms. This chapter involves those aspects and the related fields with emphasis in the prediction of energy consumption to optimize its usage policies.

Download Full-text

From biorefineries to bioproducts: conversion of pretreated pulp from biorefining streams to lignocellulose nanofibers

TAPPI Journal ◽

10.32964/tj18.4.233 ◽

2019 ◽

Vol 18 (4) ◽

pp. 233-241

Author(s):

CHENGGUI SUN ◽

RICHARD CHANDRA ◽

YAMAN BOLUK

Keyword(s):

Energy Consumption ◽

Enzymatic Hydrolysis ◽

Rheological Behavior ◽

Material Basis ◽

Softwood Pulp ◽

Energy Consumptions ◽

Hardwood Pulp ◽

The Stability ◽

Lignocellulose Nanofibers

This study investigates the use of pretreatment and enzymatic hydrolysis side streams and conversion to lignocellulose nanofibers. We used a steam-exploded and partial enzymatic hydrolyzed hardwood pulp and an organosolv pretreated softwood pulp to prepare lignocellulose nanofibers (LCNF) via microfluidization. The energies applied on fibrillation were estimated to examine the energy consumption levels of LCNF production. The energy consumptions of the fibrillation processes of the hardwood LCNF production and the softwood LCNF production were about 7040-14080 kWh/ton and 4640 kWh/ton on a dry material basis, respectively. The morphology and dimension of developed hardwood and softwood LCNFs and the stability and rheological behavior of their suspensions were investigated and are discussed.

Download Full-text

Analysis of Risk Factors in Dementia Through Machine Learning

Journal of Alzheimer s Disease ◽

10.3233/jad-200955 ◽

2020 ◽

pp. 1-17

Author(s):

Francisco Javier Balea-Fernandez ◽

Beatriz Martinez-Vega ◽

Samuel Ortega ◽

Himar Fabelo ◽

Raquel Leon ◽

...

Keyword(s):

Machine Learning ◽

Optimization Algorithms ◽

Progressive Increase ◽

Control Group ◽

Data Sets ◽

Modifiable Factors ◽

Validation Set ◽

The One ◽

And Control ◽

Potential Tool

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.

Download Full-text

Production of grape pekmez by Ohmic heating-assisted vacuum evaporation

Food Science and Technology International ◽

10.1177/1082013221991616 ◽

2021 ◽

pp. 108201322199161

Author(s):

Merve Tuçe Tunç ◽

Arda Akdoğan ◽

Cemalettin Baltacı ◽

Zeliha Kaya ◽

Halil İbrahim Odabaş

Keyword(s):

Energy Efficiency ◽

Energy Consumption ◽

Ohmic Heating ◽

Vacuum Evaporation ◽

Voltage Gradient ◽

Evaporation Process ◽

Significant Difference ◽

Total Process ◽

Energy Consumptions ◽

Voltage Gradients

Pekmez is a concentrated syrup-like food conventionally produced by vacuum evaporation process from sugar-rich fruits. In this study, the applicability of grape pekmez production by ohmic heating assisted vacuum evaporation (ΩVE) method was investigated. Conventional vacuum evaporation (CVE) and ΩVE methods were compared in terms of physicochemical properties, HMF (5-hydroxymethylfurfural) contents, rheological properties, and energy consumptions. ΩVE was run at four different voltage gradients (17.5, 20, 22.5, and 25 V/cm). Total process times for grape pekmez production were determined as 57, 28.5, 32, 39, and 50 minutes for CVE, ΩVE (25 V/cm), ΩVE (22.5 V/cm), ΩVE (20 V/cm) and ΩVE (17.5 V/cm), respectively. Energy consumption of CVE method was higher than ΩVE method for all voltage gradients. Energy efficiency increased as the voltage gradient increased. There was no significant difference between CVE and ΩVE methods for HMF contents. The results show that the ΩVE method could be an alternative to the CVE process for grape pekmez production.

Download Full-text

Machine Learning-Based Models for the Estimation of the Energy Consumption in Metal Forming Processes

Metals ◽

10.3390/met11050833 ◽

2021 ◽

Vol 11 (5) ◽

pp. 833

Author(s):

Irene Mirandola ◽

Guido A. Berti ◽

Roberto Caracciolo ◽

Seungro Lee ◽

Naksoo Kim ◽

...

Keyword(s):

Machine Learning ◽

Finite Element ◽

Energy Consumption ◽

Metal Forming ◽

Mutual Influence ◽

Rolling Process ◽

Ring Rolling ◽

Gradient Boosting ◽

Average Error ◽

Ring Rolling Mill

This research provides an insight on the performances of machine learning (ML)-based algorithms for the estimation of the energy consumption in metal forming processes and is applied to the radial-axial ring rolling process. To define the mutual influence between ring geometry, process settings, and ring rolling mill geometries with the resulting energy consumption, measured in terms of the force integral over the processing time (FIOT), FEM simulations have been implemented in the commercial SW Simufact Forming 15. A total of 380 finite element simulations with rings ranging from 650 mm < DF < 2000 mm have been implemented and constitute the bulk of the training and validation datasets. Both finite element simulation settings (input), as well as the FI (output), have been utilized for the training of eight machine learning models, implemented with Python scripts. The results allow defining that the Gradient Boosting (GB) method is the most reliable for the FIOT prediction in forming processes, being its maximum and average errors equal to 9.03% and 3.18%, respectively. The trained ML models have been also applied to own and literature experimental cases, showing a maximum and average error equal to 8.00% and 5.70%, respectively, thus proving once again its reliability.

Download Full-text

Effect of Roof Cooling and Air Curtain Gates on Thermal and Wind Conditions in Stadiums for Hot Climates

Energies ◽

10.3390/en14133941 ◽

2021 ◽

Vol 14 (13) ◽

pp. 3941

Author(s):

Fangliang Zhong ◽

Hassam Nasarullah Chaudhry ◽

John Kaiser Calautit

Keyword(s):

Energy Consumption ◽

Electric Energy ◽

Building Energy ◽

Future Research ◽

World Cup ◽

Air Curtain ◽

Hot Air ◽

Computational Fluid Dynamics Cfd ◽

Energy Consumptions ◽

The Spectator

To host the 2022 FIFA World Cup, Qatar is facing the greatest challenge in balancing the energy consumptions for cooling the stadiums and the thermal comfort for both players and spectators. Previous studies have not considered using a combined configuration of air curtain and roof cooling supply slot in stadiums to prevent the infiltration of outside hot air and reduce the cooling system’s energy consumption. This paper presents a Computational Fluid Dynamics (CFD) study of thermal and wind modeling around a baseline stadium and simulates the cooling scenarios of air curtains and roof cooling along with the energy consumption estimations for the World Cup matches using Building Energy Simulation (BES). Sensitivity analysis of different supply speeds and supply temperatures of air curtain gates and roof cooling was carried out, and the results showed that scenario six, which provides supply air of 25 m/s and 20 m/s at the roof and air curtain gates with a supply temperature of 10 °C, demonstrates optimal thermal performances on both the spectator tiers and the pitch. Compared with the baseline stadium performance, the average reductions in temperature on the pitch and spectator tiers under scenario six could reach 15 °C and 14.6 °C. The reductions in the Predicted Percentage of Dissatisfied values for the upper and lower tiers as well as the pitch were 63%, 74%, and 78%. In terms of the estimated energy consumptions, scenario six would consume electric energy per match at a rate of 25.5 MWh compared with 22.8 MWh for one of the stadiums in the 2010 South Africa World Cup and 42.0 MWh for the 2006 Germany World Cup. Future research is recommended to explore the influence of supply angle on air curtain gates and roof cooling supply slots’ performances.

Download Full-text