Application of short term energy consumption forecasting for household energy management system

Ahmed, Kazi Main Uddin; Amin, M. Abdullah Al; Rahman, Md. Ashib

doi:10.1109/icget.2015.7315095

Cited by 6 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…El constante incremento del consumo de energía eléctrica (CEE) [1][2], estrechamente ligado al desarrollo socioeconómico [3][4], se ha convertido en uno de los temas que más ocupa la atención de políticos y científicos, tanto para determinar políticas de energía [3][4][5] como para considerar la disminución de costos en todos los puntos de su proceso de producción (generación, distribución y consumo, con énfasis en este último) [6][7] y preservar el medio ambiente [8][9]. La marcada tendencia a la desregulación del mercado de la energía eléctrica [10][11], los cambios climáticos [12][13], la expansión del uso de las energías renovables [14] y la escasez de combustibles fósiles hacen más complejo el escenario; por lo tanto, contar con pronósticos de CEE que den cuenta acabadamente de esta complejidad se vuelve un desafío.…”

Section: Introductionunclassified

“…Las investigaciones en pronóstico de CEE abarcan un conjunto variado de diferentes aristas del problema, por esta razón se encuentran, tanto trabajos referidos a pronósticos de consumo a largo plazo [1][2][3][4][5], que parten de considerar la correspondencia entre factores socioeconómicos y valores de consumo, como de mediano [4][5][6][7][8] y corto plazo [15][16] donde se consideran otras variables como la temperatura y el día de la semana. Resulta recurrente en la mayoría de los estudios revisados, la dificultad que reviste la selección de variables de entrada [10][11][12][13][14][15][16][17], ya sea por determinar cuáles considerar/no considerar o por la cantidad de datos históricos que habría que incluir, haciendo más compleja aún la definición del modelo de pronóstico.…”

Section: Introductionunclassified

“…De forma general, en los estudios sobre pronóstico de CEE y de acuerdo con las restricciones identificadas, se seleccionan los modelos más adecuados o se considera la definición de un nuevo modelo. El objetivo en la mayoría de los casos es encontrar aquel modelo del que se obtengan los pronósticos más precisos, al tiempo que pueda atender la variabilidad de las condiciones en las que tiene lugar el consumo [11][12][13][14][15][16][17], por ejemplo, adaptarse a los cambios en los patrones de comportamiento de los consumidores, temperatura ambiental, luminosidad, etc. Para ello, en varios estudios se realizan análisis comparativos entre modelos preexistentes y el modelo propuesto a través de técnicas de medición de error, determinándose el porcentaje de mejora que aportan y en qué aspectos de su desempeño resultan particularmente superiores (por ejemplo, costos computacionales y tiempos de entrenamiento) [16].…”

Section: Introductionunclassified

See 2 more Smart Citations

Revisión sistemática de literatura sobre modelos de pronósticos de consumo de energía eléctrica

Mazzeo

Sepúlveda-Cano

Montoya

et al. 2019

rev.ing.univ.Medellin

View full text Add to dashboard Cite

El creciente consumo de energía eléctrica, los cambios climáticos y el desarrollo de nuevas tecnologías exigen mejoras para la gestión eficiente de la energía. El adecuado pronóstico del consumo de energía es relevante para el desarrollo sostenible de cualquier país. En este artículo se propone una revisión sistemática de literatura seleccionada a partir de cadenas de búsqueda formada por las palabras forecasting, energyy consumptionaplicadas en las bases de datos científicas. Se comparan principalmente los modelos/técnicas utilizadas, las variables consideradas y las métricas de error usadas con el fin de obtener conocimiento de cada una de las propuestas, relevar sus características y así poder evidenciar el vacío en la literatura que podría determinar la semilla para un nuevo trabajo de investigación. Como conclusiones se observan el uso continuo de redes neuronales artificiales para el pronóstico de consumo, la importancia determinar las variables de entrada y la medición del error para evaluar la precisión de los modelos. Finalmente, como nueva línea de investigación se propone desarrollar un modelo para el pronóstico de corto plazo de CEE para un país latinoamericano en vías de desarrollo, a partir de la comparación y evaluación de diferentes técnicas/modelos, variables y herramientas ya existentes.

show abstract

Section: Introductionunclassified

See 1 more Smart Citation

Revisión sistemática de literatura sobre modelos de pronósticos de consumo de energía eléctrica

Mazzeo

Sepúlveda-Cano

Montoya

et al. 2019

rev.ing.univ.Medellin

View full text Add to dashboard Cite

show abstract

“…This is one of the major issues leading to the different challenges in household-based energy consumption forecasting. The studies in [22][23][24] discuss the importance and the difficulties in forecasting the energy consumption at the household level.…”

Section: Introductionmentioning

confidence: 99%

Robust ensemble learning framework for day-ahead forecasting of household based energy consumption

2018

View full text Add to dashboard Cite

Smart energy management mandates a more decentralized energy infrastructure, entailing energy consumption information on a local level. Household-based energy consumption trends are becoming important to achieve reliable energy management for such local power systems. However, predicting energy consumption on a household level poses several challenges on technical and practical levels. The literature lacks studies addressing prediction of energy consumption on an individual household level. In order to provide a feasible solution, this paper presents a framework for predicting the average daily energy consumption of individual households. An ensemble method, utilizing information diversity, is proposed to predict the day-ahead average energy consumption. In order to further improve the generalization ability, a robust regression component is proposed in the ensemble integration. The use of such robust combiner has become possible due to the diversity parameters provided in the ensemble architecture. The proposed approach is applied to a case study in France. The results show significant improvement in the generalization ability as well as alleviation of several unstable-prediction problems, existing in other models. The results also provide insights on the ability of the suggested ensemble model to produce improved prediction performance with limited data, showing the validity of the ensemble learning identity in the proposed model. We demonstrate the conceptual benefit of ensemble learning, emphasizing on the requirement of diversity within datasets, given to sub-ensembles, rather than the common misconception of data availability requirement for improved prediction.

show abstract

“…Authors used artificial neural networks (ANN) and least squares support vector regression (LS-SVR) and the latter method achieved the best overall mean absolute percentage error (MAPE) ranged between 16 and 21% for the three households. Ahmed et al [7] used ANN to predict day ahead household loads with 15 min resolution. Although the household stock consisted of 28 households, authors presented results for a single household for a limited of 15 days test period where the model achieved MAPE of 13.90%.…”

Section: Introductionmentioning

confidence: 99%

Short-term forecasting of individual household electricity loads with investigating impact of data resolution and forecast horizon

Yildiz

Bilbao

Dore

et al. 2018

Renew. Energy Environ. Sustain.

View full text Add to dashboard Cite

Smart grid components such as smart home and battery energy management systems, high penetration of renewable energy systems, and demand response activities, require accurate electricity demand forecasts for the successful operation of the electricity distribution networks. For example, in order to optimize residential PV generation and electricity consumption and plan battery charge-discharge regimes by scheduling household appliances, forecasts need to target and be tailored to individual household electricity loads. The recent uptake of smart meters allows easier access to electricity readings at very fine resolutions; hence, it is possible to utilize this source of available data to create forecast models. In this paper, models which predominantly use smart meter data alongside with weather variables, or smart meter based models (SMBM), are implemented to forecast individual household loads. Well-known machine learning models such as artificial neural networks (ANN), support vector machines (SVM) and Least-Square SVM are implemented within the SMBM framework and their performance is compared. The analysed household stock consists of 14 households from the state of New South Wales, Australia, with at least a year worth of 5 min. resolution data. In order for the results to be comparable between different households, our study first investigates household load profiles according to their volatility and reveals the relationship between load standard deviation and forecast performance. The analysis extends previous research by evaluating forecasts over four different data resolution; 5, 15, 30 and 60 min, each resolution analysed for four different horizons; 1, 6, 12 and 24 h ahead. Both, data resolution and forecast horizon, proved to have significant impact on the forecast performance and the obtained results provide important insights for the operation of various smart grid applications. Finally, it is shown that the load profile of some households vary significantly across different days; as a result, providing a single model for the entire period may result in limited performance. By the use of a pre-clustering step, similar daily load profiles are grouped together according to their standard deviation, and instead of applying one SMBM for the entire data-set of a particular household, separate SMBMs are applied to each one of the clusters. This preliminary clustering step increases the complexity of the analysis however it results in significant improvements in forecast performance. *

show abstract

Application of short term energy consumption forecasting for household energy management system

Cited by 6 publications

References 13 publications

Revisión sistemática de literatura sobre modelos de pronósticos de consumo de energía eléctrica

Revisión sistemática de literatura sobre modelos de pronósticos de consumo de energía eléctrica

Robust ensemble learning framework for day-ahead forecasting of household based energy consumption

Short-term forecasting of individual household electricity loads with investigating impact of data resolution and forecast horizon

Contact Info

Product

Resources

About