Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island

Saglam, Mustafa; Spataru, Catalina; Karaman, Ömer Ali

doi:10.3390/en15165950

Cited by 20 publications

(33 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLR model is a methodology that establishes the causal relationship between independent and dependent variables through a mathematical framework. The MLR model accurately defines the connections among these variables, precisely characterising their associations [3].…”

Section: Multiple Linear Regression Modellingmentioning

confidence: 99%

See 1 more Smart Citation

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Saglam,

Lv,

Spataru

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

Accurate instantaneous electricity peak load prediction is crucial for efficient capacity planning and cost-effective electricity network establishment. This paper aims to enhance the accuracy of instantaneous peak load forecasting by employing models incorporating various optimization and machine learning (ML) methods. This study examines the impact of independent inputs on peak load estimation through various combinations and subsets using multilinear regression (MLR) equations. This research utilizes input data from 1980 to 2020, including import and export data, population, and gross domestic product (GDP), to forecast the instantaneous electricity peak load as the output value. The effectiveness of these techniques is evaluated based on error metrics, including mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R2. The comparison extends to popular optimization methods, such as particle swarm optimization (PSO), and the newest method in the field, including dandelion optimizer (DO) and gold rush optimizer (GRO). This comparison is made against conventional machine learning methods, such as support vector regression (SVR) and artificial neural network (ANN), in terms of their prediction accuracy. The findings indicate that the ANN and GRO approaches produce the least statistical errors. Furthermore, the correlation matrix indicates a robust positive linear correlation between GDP and instantaneous peak load. The proposed model demonstrates strong predictive capabilities for estimating peak load, with ANN and GRO performing exceptionally well compared to other methods.

show abstract

Section: Multiple Linear Regression Modellingmentioning

confidence: 99%

“…Electricity load forecasting aims to achieve a harmonious balance between production and consumption, utilizing the potential of forecasting models [2,3]. Precise electricity load forecasting can mitigate the risk of power outages and reduce the expenses associated with surplus electricity generation capacity.…”

Section: Introductionmentioning

confidence: 99%

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Saglam,

Lv,

Spataru

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, in terms of comparing the suitability of the artificial intelligence models, the evidence in the literature is mixed as to the most optimum machine learning algorithm to model electricity demand. For instance, Abdusalam et al (2016), Melodi et al (2017), Saglam et al (2022), andHasanah et al (2020) provided evidence that supports the optimal performance of neural network ML algorithm; however, Chapagain et al (2020), Yotto et al (2023 and Eya et al (2023) refuted their optimal performance. However, studies about electricity demand modelling using ML techniques for Nigeria, such as Abdusalam et al (2016), Melodi et al (2017) and Adewuyi et al (2020) adopted the neural network algorithms, but Eya et al (2023) that also used the neural network algorithms for Nigeria reported that the algorithm underperformed compared to artificial neuro-fuzzy inference system (ANFIS) algorithm.…”

Section: Table 23 Herementioning

confidence: 99%

Investigating the Drivers of Grid Electricity Demand in Nigeria: Harnessing the Power of Machine Learning and Artificial Intelligence Algorithms

Olubusoye,

Emmanuel,

Nwobi

et al. 2023

Preprint

View full text Add to dashboard Cite

The electricity situation in Nigeria is epileptic, and several households rely on alternative sources of electricity to power homes and businesses. In an urban area of the country, four (4) out of every six (6) households operate an alternative electricity supply. On the other hand, individuals in rural areas can hardly afford alternative electricity sources. More so, urban individuals use mostly alternative sources that are non-renewable (such as generators), thereby causing environmental degradation and promoting Climate-related issues. The direct impact of these alternative electricity sources has led to the death of entire families due to carbon monoxide breathing by household occupants/family and caused detrimental health issues to nearby households on several occasions. To address electricity instability issues and promote a sustainable and reliable green energy future, it is worthwhile to identify the factors influencing the grid electricity demand and develop efficient models for identifying these factors and their influence on grid electricity demand. The study finds that classical algorithms are ultimately inefficient due to the multicollinearity component of the relevant features. Consequently, the study harnesses the power of Blackbox and Glassbox algorithms - Deep Neural Network (DNN) and Multivariate Adaptive Regression Spline (MARS), respectively, to investigate these factors. The two learning algorithms agreed that Nigeria's electricity demand is majorly driven by Macroeconomic and Climatology variables – with Rural population, Temperature and GDP per capita being the most relevant drivers of electricity demand in Nigeria. Given the relevance of the GDP per capita, the result implies that the discrepancies in the socioeconomic characteristics of households or individuals in Urban to Rural played a major role in the electricity demand in Nigeria. Hence, the study concludes that by addressing only Electricity problems, Nigeria will achieve fifty-three (53) percent of the global SDG agenda and greater economic development.

show abstract

“…The authors in [ 10 ] investigate electricity demand forecasting using artificial intelligence techniques, focusing on Gokceada Island as a case study. While this study does not directly address electricity theft, it underscores the importance of accurate forecasting methods in managing energy resources effectively.…”

Section: Introductionmentioning

confidence: 99%

Hyperparameter Optimization with Genetic Algorithms and XGBoost: A Step Forward in Smart Grid Fraud Detection

Mehdary,

Chehri,

Jakimi

et al. 2024

Sensors

View full text Add to dashboard Cite

This study provides a comprehensive analysis of the combination of Genetic Algorithms (GA) and XGBoost, a well-known machine-learning model. The primary emphasis lies in hyperparameter optimization for fraud detection in smart grid applications. The empirical findings demonstrate a noteworthy enhancement in the model’s performance metrics following optimization, particularly emphasizing a substantial increase in accuracy from 0.82 to 0.978. The precision, recall, and AUROC metrics demonstrate a clear improvement, indicating the effectiveness of optimizing the XGBoost model for fraud detection. The findings from our study significantly contribute to the expanding field of smart grid fraud detection. These results emphasize the potential uses of advanced metaheuristic algorithms to optimize complex machine-learning models. This work showcases significant progress in enhancing the accuracy and efficiency of fraud detection systems in smart grids.

show abstract

Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island

Cited by 20 publications

References 47 publications

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Investigating the Drivers of Grid Electricity Demand in Nigeria: Harnessing the Power of Machine Learning and Artificial Intelligence Algorithms

Hyperparameter Optimization with Genetic Algorithms and XGBoost: A Step Forward in Smart Grid Fraud Detection

Contact Info

Product

Resources

About