Analysis of modern approaches for the prediction of electric energy consumption

Kalimoldayev, Maksat; Drozdenko, A.A.; Koplyk, Igor; Маринич, Тетяна Олександрівна; Abdildayeva, Assel; Zhukabayeva, Tamara

doi:10.1515/eng-2020-0028

Cited by 26 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weather conditions are identified as the main factor determining the production of green energy and the demand for electricity. Additional independent factors, such as holidays, operational characteristics of buildings, and indicators of living standards, are also identified to influence the demand (Hong et al 2020;Kalimoldayev et al 2020). These advancements in forecast form the basis to drive research work on dynamic pricing of electricity and implementing DR systems (Kalimoldayev et al 2020).…”

Section: Machine Learning and Forecasting Methodsmentioning

confidence: 99%

“…Additional independent factors, such as holidays, operational characteristics of buildings, and indicators of living standards, are also identified to influence the demand (Hong et al 2020;Kalimoldayev et al 2020). These advancements in forecast form the basis to drive research work on dynamic pricing of electricity and implementing DR systems (Kalimoldayev et al 2020). The influence of DR systems has also been evaluated with the use of deep learning methods.…”

Section: Machine Learning and Forecasting Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning

Wicaksono

Boroukhian

Bashyal

2021

Dynamics in Logistics

View full text Add to dashboard Cite

The spread of demand-response (DR) programs in Europe is a slow but steady process to optimize the use of renewable energy in different sectors including manufacturing. A demand-response program promotes changes of electricity consumption patterns at the end consumer side to match the availability of renewable energy sources through price changes or incentives. This research develops a system that aims to engage manufacturing power consumers through price- and incentive-based DR programs. The system works on data from heterogeneous systems at both supply and demand sides, which are linked through a semantic middleware, instead of centralized data integration. An ontology is used as the integration information model of the semantic middleware. This chapter explains the concept of constructing the ontology by utilizing relational database to ontology mapping techniques, reusing existing ontologies such as OpenADR, SSN, SAREF, etc., and applying ontology alignment methods. Machine learning approaches are developed to forecast both the power generated from renewable energy sources and the power demanded by manufacturing consumers based on their processes. The forecasts are the groundworks to calculate the dynamic electricity price introduced for the DR program. This chapter presents different neural network architectures and compares the experiment results. We compare the results of Deep Neural Network (DNN), Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), and Hybrid architectures. This chapter focuses on the initial phase of the research where we focus on the ontology development method and machine learning experiments using power generation datasets.

show abstract

Section: Machine Learning and Forecasting Methodsmentioning

confidence: 99%

Section: Machine Learning and Forecasting Methodsmentioning

confidence: 99%

A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning

Wicaksono

Boroukhian

Bashyal

2021

Dynamics in Logistics

View full text Add to dashboard Cite

show abstract

“…They assessed the key benefits and drawbacks of the available modeling techniques and applied them to the energy systems of Kazakhstan and Ukraine. Furthermore, they identified the main factors affecting the dynamics of energy consumption and prepared a list of the main tasks that should be implemented to develop algorithms to forecast electricity demand for objects, industries, and different levels [45].…”

Section: Literature Reviewmentioning

confidence: 99%

Oil Demand Forecasting in Importing and Exporting Countries: AI-Based Analysis of Endogenous and Exogenous Factors

Zhu

2023

Sustainability

View full text Add to dashboard Cite

Given the prevalence of the digital world, artificial intelligence (AI) stands out as one of the most prominent technologies for demand prediction. Although numerous studies have explored energy demand forecasting using machine learning models, previous research has been limited to incorporating either a country’s macroeconomic characteristics or exogenous elements as input variables. The simultaneous consideration of both endogenous and exogenous economic elements in demand forecasting has been disregarded. Furthermore, the stability of machine learning models for energy exporters and importers facing varying uncertainties has not been adequately examined. Therefore, this study aims to address these gaps by investigating these issues comprehensively. To accomplish this objective, data from 30 countries spanning the period from 2000 to 2020 was selected. In predicting oil demand, endogenous economic variables, such as carbon emissions, income level, energy price, gross domestic product (GDP), population growth, urbanization, trade liberalization, inflation, foreign direct investment (FDI), and financial development, were considered alongside exogenous factors, including energy sanctions and the COVID-19 pandemic. The findings indicate that among the input variables examined in demand forecasting, oil sanctions and the COVID-19 pandemic have had the most significant impact on reducing oil demand, while trade liberalization has proven to be the most influential factor in increasing oil demand. Furthermore, the support vector regression (SVR) model outperforms other models in terms of lower prediction error, as revealed by the error assessment of statistical models and AI in forecasting oil demand. Additionally, when comparing the stability of models in oil exporting and importing countries facing different levels of demand uncertainty, the SVR model demonstrates higher stability compared to other models.

show abstract

“…Feedback-based strategies are necessary to assess learners' performance when dealing with concept drift [15]. For continuous variables, root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are the most commonly used performance metrics for measuring accuracy and the average size of errors in a prediction set [43]. However, because RMSE gives significant errors a greater load, it is advantageous when such errors should be avoided.…”

Section: B Performance Metricsmentioning

confidence: 99%

Dynamic Modeling With Integrated Concept Drift Detection for Predicting Real-Time Energy Consumption of Industrial Machines

2022

View full text Add to dashboard Cite

Industrial machinery is a significant energy consumer, and its CO 2 emissions have increased dramatically in recent years. Therefore, energy efficiency is becoming crucial for businesses, governments, as well as the planet. Estimating the power consumption of industrial machines with greater accuracy assists management and optimizes machine operation parameters. Real-time industrial machine datasets present several challenges, such as changes in the data over time, unknown running conditions, missing data, etc. Most research publications focus on the accuracy of traditional static models of forecasting; however, prediction performance deteriorates over time because data evolves. We implemented deep learning as a prediction model for three distinct real-world industrial datasets. The proposed method, dynamic modeling with memory (DMWM), improved overall prediction performance compared with conventional approaches by identifying concept drifts and optimizing the number of required models in response to industrial datasets' recurring machine energy consumption patterns.

show abstract

Analysis of modern approaches for the prediction of electric energy consumption

Cited by 26 publications

References 31 publications

A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning

A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning

Oil Demand Forecasting in Importing and Exporting Countries: AI-Based Analysis of Endogenous and Exogenous Factors

Dynamic Modeling With Integrated Concept Drift Detection for Predicting Real-Time Energy Consumption of Industrial Machines

Contact Info

Product

Resources

About