Clustering Techniques Selection for a Hybrid Regression Model: A Case Study Based on a Solar Thermal System

Garcí­a-Ordás, María Teresa; Aláiz‐Moretón, Héctor; Casteleiro‐Roca, José‐Luis; Jove, Esteban; Bení­tez-Andrades, José Alberto; García-Rodríguez, Isaías; Quintián, Héctor; Calvo-Rolle, José Luís

doi:10.1080/01969722.2022.2030006

Cited by 9 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The contour coefficients and Calinski-Harabaz index coefficients of each algorithm in clusters ranging from 2 to 10 are calculated, and the clustering performance of each algorithm in each cluster is compared. The corresponding expressions are shown in equations ( 9) to (11) [32][33][34].…”

Section: B Selection and Correction Of Urban Building Energy Consumpt...mentioning

confidence: 99%

Construction and Research of a Data-Driven Energy Consumption Evaluation Model for Urban Building Operation

Gao,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

The bottom-up simulation method of building energy consumption, which mainly focuses on individual buildings, is difficult to apply to urban and regional level building energy consumption planning. Therefore, based on data-driven research, a simulation evaluation model for extreme gradient boosting at the mesoscale and K-means energy consumption at the macro scale is proposed and validated. The experimental results show that in the mesoscale model simulation prediction, in terms of training time comparison, the support vector method and sequential model have a time of 138.69 seconds and 90.00 seconds, respectively, which is much higher than other algorithms. The random forest algorithm has the highest accuracy comparison, at 83%; In the comparison of accuracy recall rate, the gradient improvement decision tree algorithm has the highest accuracy, at 83%. The extreme gradient boosting model proposed based on it has a mean square error value of 11.45 in residential sample prediction under refrigeration load and 9.16 under heating load, both of which are better than the comparative model. Applying it to practice, it is found that the correlation between building heating and cooling load and the 8 variables of the building is clearly demonstrated. In the macro scale model simulation prediction, the overall effect of K-means model I is the best under the comparison of contour coefficients, with the highest value maintained at around 0.1 when the number of clusters is 10. By applying it in practice, the spatial distribution of load can be clearly demonstrated, and the predicted value of total energy supply in the constructed regression equation is highly consistent with the actual value. Overall, the simulation and evaluation model for urban building energy consumption proposed in the study at two scales is practical and can effectively accelerate the development and improvement of urban energy systems.In addition, the research method considers the relevant operational energy consumption throughout the entire life cycle and the dynamic energy consumption of urban transportation systems, and provides reference value for existing urban renovation, thus possessing innovation.INDEX TERMS Data-driven, Urban architecture, Energy consumption evaluation model, Simulation methods, ML

show abstract

Section: B Selection and Correction Of Urban Building Energy Consumpt...mentioning

confidence: 99%

Construction and Research of a Data-Driven Energy Consumption Evaluation Model for Urban Building Operation

Gao,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Figura 1: Ejemplo de anomalías Debido a la creciente complejidad de los sistemas, así como al continuo desarrollo computacional, en los últimos años muchas líneas de investigación se han centrado en la detección de anomalías o fallos en una gran cantidad de sistemas y campos, tales como, la medicina [12,19,20,22,25,13], la economía [24], la informática [23,9] o la industria [2,7,8,11,3,17,18], entre otros.…”

Section: Introductionunclassified

Técnicas de clasificación supervisadas para la detección de anomalías en el control de procesos industriales

Michelena¹,

Zayas‐Gato²,

Jove³

et al. 2022

XLIII Jornadas De Automática: Libro De Actas: 7, 8 Y 9 De Septiembre De 2022, Logroño (La Rioja)

Self Cite

View full text Add to dashboard Cite

En la actualidad la detección de anomalías en procesos industriales es clave para optimizarlos y generar una mayor eficiencia en el proceso productivo, reportando unos mayores beneficios a las empresas. Por ello, en el presente artículo se implementan cinco técnicas de clasificación supervisadas para la detección de anomalías en sistemas industriales. Estas técnicas han sido entrenadas y validadas empleando un conjunto de datos que incluían datos etiquetados de funcionamiento normal y anómalo de una planta de control de nivel de líquido en un depósito. Finalmente, los resultados obtenidos fueron analizados y comparados para obtener el modelo con el que se obtiene un mayor rendimiento.

show abstract

A HAIS Approach to Predict the Energy Produced by a Solar Panel

Arroyo

Quintián

Calvo-Rolle

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Clustering Techniques Selection for a Hybrid Regression Model: A Case Study Based on a Solar Thermal System

Cited by 9 publications

References 29 publications

Construction and Research of a Data-Driven Energy Consumption Evaluation Model for Urban Building Operation

Construction and Research of a Data-Driven Energy Consumption Evaluation Model for Urban Building Operation

Técnicas de clasificación supervisadas para la detección de anomalías en el control de procesos industriales

A HAIS Approach to Predict the Energy Produced by a Solar Panel

Contact Info

Product

Resources

About