Electrical Energy Demand Forecasting Using Artificial Neural Network

Unutmaz, Yesim Esra; Demirci, Alpaslan; Tercan, Said Mirza; Yumurtacı, Recep

doi:10.1109/hora52670.2021.9461186

Cited by 7 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recursive neural networks were used in the study of Unutmaz et al [19] for long-term load forecasting. Using a three-layer artificial neural network (ANN) and the backpropagation learning technique, the article emphasised how important economic development is.…”

Section: Literature Reviewmentioning

confidence: 99%

Long-term Load Forecasting for Optimal Power System Planning and Decision-Making

Amadi,

Awochi,

Innocent

2024

JERR

View full text Add to dashboard Cite

Forecasting the future load growth of an area based on its load demand is often a proactive measure to ensure a steady electricity power supply to that area. The study focused on long-term load forecasting for power system planning, specifically examining the electric load demand from consumers on distribution transformers within Port Harcourt City, located in Rivers State, Nigeria. The study encompassed a comprehensive review of both statistical and artificial intelligence-based approaches. Historical load data for distribution transformer readings spanning 2008 to 2017 were acquired from the Port Harcourt Electricity Distribution Company (PHEDC) and subjected to analysis using the curve-fitting technique. For the period between 2015 and 2030, a yearly load forecast simulation was conducted using the Fourier Series model, implemented with MATLAB software. This simulation aimed to provide insights into future load demand, facilitating careful and informed decision-making in the investment, operation, and maintenance of power system equipment. The effectiveness of the forecasting investigation was assessed using the Root Mean Square Error (RMSE), confirming the efficiency, reliability, and validity of the employed model. The study's forecasted results are presented as a valuable guide and practical tool for policymakers and the utility company (PHEDC) to enhance proper planning and decision-making processes. Considering the observed trend in the results, it is suggested that installing additional transformer units in the region would be necessary to alleviate the loads on existing overloaded transformer units within the power system network.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Long-term Load Forecasting for Optimal Power System Planning and Decision-Making

Amadi,

Awochi,

Innocent

2024

JERR

View full text Add to dashboard Cite

show abstract

“…Many studies are also carried out to predict the addition of energy needs in every region. In [2] has conducted research on the prediction of electricity demand by utilizing artificial neural networks (ANN). In Indonesia, research on predicting energy consumption has been conducted by [3][4] recently.…”

Section: Introductionmentioning

confidence: 99%

Numerical and experimental study of mixed flow pump as turbine for remote rural micro hydro power plant application

Mejiartono¹,

Hikmawan²,

Nugraha³

2022

J. Mechatron. Electr. Power Veh. Technol.

View full text Add to dashboard Cite

The use of a pump as opposed to a turbine/pump as turbine (PAT) for off-grid electrification applications is one of the important ways to be considered in efforts to equalize electrical energy in Indonesia. The main problem in PAT applications is how to predict pump performance if applied as a turbine to find out its best characteristics and efficiency points. This study discusses a method to find pump performance specifications when using a pump with a mixed flow type as a turbine for Micro Hydro Power Plants. The numerical method by utilizing computational Fluid Dynamics (CFD) based software simulations that have been proven to be accurate according to previous studies was selected for use in obtaining predictions of the pump characteristics as turbines. Then the PAT characteristics of the CFD simulation results are validated by conducting direct testing. The results of the CFD numerical simulation using ANSYS Fluent software show the performance curve of a mixed flow pump operated as a turbine at various rotating speeds. The highest efficiency for each rotating speed ranges from 35-40%. The test results directly show the PAT characteristics, that the performance range is close to the numerical simulation results with a difference of 10%.

show abstract

Influence of Geodemographic Factors on Electricity Consumption and Forecasting Models

2022

View full text Add to dashboard Cite

The residential sector is a major consumer of electricity, and its demand will rise by 65 percent by the end of 2050. The electricity consumption of a household is determined by various factors, e.g. house size, socio-economic status of the family, size of the family, etc. These factors play a critical role in analyzing the energy consumption causalities in the residential sector for better energy prediction models, effective price policy implementations, and improved customer engagement in energy efficiency programs. However, determining the effect of demographic factors on energy consumption is a challenging prospect. First, it is not trivial to study the causes of energy consumption variation, even for similar size residential houses, without analyzing the impact of interdependencies between demographic factors on energy consumption behavior. Second, to achieve higher accuracy of energy prediction models, it is necessary to identify key geodemographic factors that influence these models. Previous studies have only identified a limited number of socio-economic and dwelling factors. In this paper, we study the significance of 826 geodemographic factors on electricity consumption for 4917 homes in the City of London. Geodemographic factors cover a wide array of categories e.g. social, economic, dwelling, family structure, health, education, finance, occupation, and transport. Using Spearman correlation, we have identified 354 factors that are strongly correlated with electricity consumption. We also examine the impact of using geodemographic factors in designing forecasting models. In particular, we develop an encoderdecoder LSTM model which shows improved accuracy with geodemographic factors. We believe that our study will help energy companies design better energy management strategies. INDEX TERMSSocio-economic factors, geodemographic factors, electricity forecasting, encoder-decoder model

show abstract

Electrical Energy Demand Forecasting Using Artificial Neural Network

Cited by 7 publications

References 12 publications

Long-term Load Forecasting for Optimal Power System Planning and Decision-Making

Long-term Load Forecasting for Optimal Power System Planning and Decision-Making

Numerical and experimental study of mixed flow pump as turbine for remote rural micro hydro power plant application

Influence of Geodemographic Factors on Electricity Consumption and Forecasting Models

Contact Info

Product

Resources

About