Electric Load Analysis and Forecasting Using Artificial Neural Networks

Fernandes, Karen Clarina; Sardinha, Razia; Rebelo, Sulana; Singh, Ramandeep

doi:10.1109/icoei.2019.8862695

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding the machine‐learning models, there are three models widely used for demand forecasting tasks, viz., DT [2, 33, 34], SVM [3, 35–37] and artificial neural network (ANN) [38–41]. DT is used to predict building energy demand levels [34] and analyse the electricity load level based on hourly observations of the electricity load and weather [33].…”

Section: Related Workmentioning

confidence: 99%

“…Recently, researchers take the advantage of LSTM to forecast building energy load using historical consumption data [40]. Historical load data and ambient temperature are utilised to build a prediction model based on ANN in [41]. Cheng et al [42] further manage to feed the concatenation of historical data and influence features as a sequential input to the LSTM network.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

PowerNet: a smart energy forecasting architecture based on neural networks

Cheng

Mashima

et al. 2020

IET Smart Cities

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

PowerNet: a smart energy forecasting architecture based on neural networks

Cheng

Mashima

et al. 2020

IET Smart Cities

View full text Add to dashboard Cite

“…Классические методы являются наиболее распространенными [5], к которым относятся аналитические, статистические и экспертные методы [7]. В настоящее время машинное обучение и искусственный интеллект сильно развиваются, основными видами машинного обучения в задачах прогнозирования электропотребления являются метод опорных векторов [8], нечеткая логика [9], нейронные сети [10,11] и ансамблемые модели [11,12].…”

Section: Introductionunclassified

Forecasting the daily energy load schedule of working days using meteofactors for the central power system of Mongolia

Rusina

Tuvshin

Matrenin

2022

«Izvestiya vysshikh uchebnykh zavedenii. PROBLEMY ENERGETIKI»

View full text Add to dashboard Cite

A feature of the power system is that all the processes of production, transmission and distribution occur simultaneously. This difficult and continuous process requires the management by the regime of the power system. For precise regime managements, it is necessary to study the characteristic of electricity consumption. Forecasting demand allows to optimize the distribution of generation and ensure the safety of the power system. Therefore, forecasting is given a lot of attention in the energy section. Although there are many forecasting methodologies, but there is no exact methodology that is suitable for all power systems.PURPOSE. To forecast the daily load schedule for working days, considering the influence of meteorological factors on the central energy system of Mongolia.METHODS. This study is carried out by the method of statistical analysis on MS Excel. As initial inputs historical data on load, temperature and outdoor air humidity of the central energy system were used, which has the most of the energy demand and sources of Mongolia by 2021.RESULTS. According to the method of statistical analysis, daily load curves were constructed with an absolute percentage error of 2.68%. After adding into account of meteorological factors, the absolute percentage error decreased to 2.26%.CONCLUSIONS. This method corresponds to forecasting daily schedules for working days. By restricting the electricity consumption during long continues non-work days, days with a major accident and planned maintenance will affect negatively to the planned tendency.

show abstract

“…To date, a number of different approaches to short-term forecasting have been proposed, starting from regression methods [12,13] and ending with machine learning approaches based on neural networks [8,14,15] and hybrid or analog forecasting methods [16,17]. A significant part of modern publications devoted to this problem are focused on the development and improvement of new information technologies for predicting time series, such as neural, fuzzy networks, genetic algorithms, etc.…”

mentioning

confidence: 99%

A Rank Analysis and Ensemble Machine Learning Model for Load Forecasting in the Nodes of the Central Mongolian Power System

Osgonbaatar,

Matrenin,

Safaraliev

et al. 2023

Inventions

View full text Add to dashboard Cite

Forecasting electricity consumption is currently one of the most important scientific and practical tasks in the field of electric power industry. The early retrieval of data on expected load profiles makes it possible to choose the optimal operating mode of the system. The resultant forecast accuracy significantly affects the performance of the entire electrical complex and the operating conditions of the electricity market. This can be achieved through using a model of total electricity consumption designed with an acceptable margin of error. This paper proposes a new method for predicting power consumption in all nodes of the power system through the determination of rank coefficients calculated directly for the corresponding voltage level, including node substations, power supply zones, and other parts of the power system. The forecast of the daily load schedule and the construction of a power consumption model was based on the example of nodes in the central power system in Mongolia. An ensemble of decision trees was applied to construct a daily load schedule and rank coefficients were used to simulate consumption in the nodes. Initial data were obtained from daily load schedules, meteorological factors, and calendar features of the central power system, which accounts for the majority of energy consumption and generation in Mongolia. The study period was 2019–2021. The daily load schedules of the power system were constructed using machine learning with a probability of 1.25%. The proposed rank analysis for power system zones increases the forecasting accuracy for each zone and can improve the quality of management and create more favorable conditions for the development of distributed generation.

show abstract

Electric Load Analysis and Forecasting Using Artificial Neural Networks

Cited by 5 publications

References 10 publications

PowerNet: a smart energy forecasting architecture based on neural networks

PowerNet: a smart energy forecasting architecture based on neural networks

Forecasting the daily energy load schedule of working days using meteofactors for the central power system of Mongolia

A Rank Analysis and Ensemble Machine Learning Model for Load Forecasting in the Nodes of the Central Mongolian Power System

Contact Info

Product

Resources

About