Forecasting performance of time series and regression in modeling electricity load demand

Jifri, Mohd Hanif; Hassan, Elia Erwani; Miswan, Nor Hamizah

doi:10.1109/icsengt.2017.8123412

Cited by 15 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such improvement is not endless, and, at d-7, the historical information is already sufficient due to the highly cyclical and periodic nature of electrical demand. A wider window width actually introduces redundant information that is irrelevant to forecasts, which actually forms the multicollinearity effect [38][39][40].…”

Section: Window Sliding Width Of Load Variablementioning

confidence: 99%

Extreme Gradient Boosting Model for Day-Ahead STLF in National Level Power System: Estonia Case Study

Zhao,

Liu,

Fang

2023

Energies

View full text Add to dashboard Cite

Short-term power load forecasting refers to the use of load and weather information to forecast the Day-ahead load, which is very important for power dispatch and the establishment of the power spot market. In this manuscript, a comprehensive study on the frame of input data for electricity load forecasting is proposed based on the extreme gradient boosting algorithm. Periodicity was the first of the historical load data to be analyzed using discrete Fourier transform, autocorrelation function, and partial autocorrelation function to determine the key width of a sliding window for an optimization load feature. The mean absolute error (MAE) of the frame reached 52.04 using a boosting model with a 7-day width in the validation dataset. Second, the fusing of datetime variables and meteorological information factors was discussed in detail and determined how to best improve performance. The datetime variables were determined as a form of integer, sine–cosine pairs, and Boolean-type combinations, and the meteorological features were determined as a combination with 540 features from 15 sampled sites, which further decreased MAE to 44.32 in the validation dataset. Last, a training method for day-ahead forecasting was proposed to combine the Minkowski distance to determine the historical span. Under this framework, the performance has been significantly improved without any tuning for the boosting algorithm. The proposed method further decreased MAE to 37.84. Finally, the effectiveness of the proposed method is evaluated using a 200-day load dataset from the Estonian grid. The achieved MAE of 41.69 outperforms other baseline models, with MAE ranging from 65.03 to 104.05. This represents a significant improvement of 35.89% over the method currently employed by the European Network of Transmission System Operators for Electricity (ENTSO-E). The robustness of the proposal method can be also guaranteed with excellent performance in extreme weather and on special days.

show abstract

Section: Window Sliding Width Of Load Variablementioning

confidence: 99%

Extreme Gradient Boosting Model for Day-Ahead STLF in National Level Power System: Estonia Case Study

Zhao,

Liu,

Fang

2023

Energies

View full text Add to dashboard Cite

show abstract

“…e results prove that the fuzzy law basis can effectively predict short-term load demand with minimal error. Jifri et al [17] showed that modeling electric charge demand is considered one of the most important areas among researchers because electricity is evolving. is study aimed to evaluate the performance of time series and regression in predicting load demand.…”

Section: Literature Reviewmentioning

confidence: 99%

Providing an Expert System to Manage Energy Consumption in Small‐ and Medium‐Sized Industries Using Soft Computing

2022

View full text Add to dashboard Cite

The increasing growth of electricity consumption, the need for its continuous supply, and the impossibility of storing this vital energy are among the primary and essential reasons for preventing any interruption in supply and proper planning regarding energy consumption management, especially in industry. The innovation of this research is the design of a decision-making system to help decision-making in energy management in small- and medium-sized industries using the knowledge of experts in small- and medium-sized industries and the electricity industry in the field of energy consumption management and extracting relevant expertise rules to create a knowledge base. Therefore, the main advantage of the research is to provide an expert system for the correct management of energy consumption in small and medium industries using soft computing. Another advantage of the research is the use of uncertain decision-making variables in this field; instead of using words and linguistic restrictions in this research, modeling them in the system using the principles of fuzzy logic is used. The main objectives of this research include determining the effective variables in determining the amount of energy production for small and medium industries, explaining the existing tacit knowledge and turning it into explicit knowledge, and providing an expert system for managing energy consumption in this field. Based on the results of field studies and the research literature, effective variables in determining the amount of electricity generation were identified. By extracting the knowledge of industry experts, the tacit knowledge available as explicit knowledge in the storage knowledge base and the system was designed to manage electrical charge consumption. One of the achievements of this system is its creation and measurement using various data and results obtained from small and medium industries. Finally, the results obtained from the expert system in comparing the output of expert opinions and the system’s performance in managing the amount of energy production showed that the usefulness of the expert system was designed. The system uses the knowledge base to make decisions such as an expert human. According to the main results of the research based on comparing the performance of the system with the Bayesian inference networks, it showed that there is an acceptable correlation between the data and the prediction system. Also, to evaluate the acquisition of data using a statistical test, it has been determined that the total number of blackout hours in different areas of Tehran in the base year was more than the current year.

show abstract

“…Some of the main advantages of TBATS are: (i) it can handle non-linearity present in features using Box-Cox transformation (ii) it detects any auto-correlation present in the residuals using ARMA and (iii) and it is capable of accommodating both nested and non-nested seasonal components in time series [75]. Its applications can be seen in some of recent studies [78], such as modelling electricity load demand [79] or seasonality of pathogens [78].…”

Section: Modelsmentioning

confidence: 99%

Concept Drift Adaptation Techniques in Distributed Environment for Real-World Data Streams

et al. 2021

View full text Add to dashboard Cite

Real-world data streams pose a unique challenge to the implementation of machine learning (ML) models and data analysis. A notable problem that has been introduced by the growth of Internet of Things (IoT) deployments across the smart city ecosystem is that the statistical properties of data streams can change over time, resulting in poor prediction performance and ineffective decisions. While concept drift detection methods aim to patch this problem, emerging communication and sensing technologies are generating a massive amount of data, requiring distributed environments to perform computation tasks across smart city administrative domains. In this article, we implement and test a number of state-of-the-art active concept drift detection algorithms for time series analysis within a distributed environment. We use real-world data streams and provide critical analysis of results retrieved. The challenges of implementing concept drift adaptation algorithms, along with their applications in smart cities, are also discussed.

show abstract

Forecasting performance of time series and regression in modeling electricity load demand

Cited by 15 publications

References 8 publications

Extreme Gradient Boosting Model for Day-Ahead STLF in National Level Power System: Estonia Case Study

Extreme Gradient Boosting Model for Day-Ahead STLF in National Level Power System: Estonia Case Study

Providing an Expert System to Manage Energy Consumption in Small‐ and Medium‐Sized Industries Using Soft Computing

Concept Drift Adaptation Techniques in Distributed Environment for Real-World Data Streams

Contact Info

Product

Resources

About