Power Consumption Forecasting Research Articles

Medium-Term Forecasting of Power Consumption by ANN Considering Meteo-Factors

The main task of forecasting power consumption is to analyze objective factors affecting load changes and compute expected schedules of consumption to support energy companies organize the purchase and production of the necessary electricity in the proper volume. However, modern practical requirements for the accuracy of predictive calculations lead to the fact that previously developed methods do not always provide the necessary accuracy of computations. This is because several factors affect the level of power consumption and the accuracy of forecasting, including meteorological, where the growing use of both wind and photovoltaic energy worldwide leads the power systems to become highly dependent on the weather conditions. This study presents the influence of meteorological factors on the medium-term forecast of electricity consumption based on the power system of the Gorno-Badakhshan Autonomous Oblast in the Republic of Tajikistan, where in winter, due to an increase in demand for electricity and a drop in the water level in rivers, to ensure balance, requires additional commissioning of diesel power plants. Thus, it leads to an increase in the costs of electricity production in the region and environmental degradation. To increase the forecasting effectiveness, the authors propose an approach based on the clustering of meteorological conditions, where each cluster has its regression model. The Principal Component Analysis was proposed for aggregating meteorological factors.

A Novel Multi-Objective Hybrid Evolutionary-Based Approach for Tuning Machine Learning Models in Short-Term Power Consumption Forecasting

Accurately forecasting power consumption is crucial important for efficient energy management. Machine learning (ML) models are often employed for this purpose. However, tuning their hyperparameters is a complex and time-consuming task. The article presents a novel multi-objective (MO) hybrid evolutionary-based approach, GA-SHADE-MO, for tuning ML models aimed at solving the complex problem of forecasting power consumption. The proposed algorithm simultaneously optimizes both hyperparameters and feature sets across six different ML models, ensuring enhanced accuracy and efficiency. The study focuses on predicting household power consumption at hourly and daily levels. The hybrid MO evolutionary algorithm integrates elements of genetic algorithms and self-adapted differential evolution. By incorporating MO optimization, GA-SHADE-MO balances the trade-offs between model complexity (the number of used features) and prediction accuracy, ensuring robust performance across various forecasting scenarios. Experimental numerical results show the superiority of the proposed method compared to traditional tuning techniques, and random search, showcasing significant improvements in predictive accuracy and computational efficiency. The findings suggest that the proposed GA-SHADE-MO approach offers a powerful tool for optimizing ML models in the context of energy consumption forecasting, with potential applications in other domains requiring precise predictive modeling. The study contributes to the advancement of ML optimization techniques, providing a framework that can be adapted and extended for various predictive analytics tasks.

Application of SHAP and Multi-Agent Approach for Short-Term Forecast of Power Consumption of Gas Industry Enterprises

Currently, machine learning methods are widely applied in the power industry to solve various tasks, including short-term power consumption forecasting. However, the lack of interpretability of machine learning methods can lead to their incorrect use, potentially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of the tasks of enhancing the energy efficiency of gas industry enterprises. In order to reduce the risks of making incorrect decisions based on the results of short-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a multi-agent approach for the decomposition of production processes using self-generation agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjusting the operation modes of self-generation units and energy-storage systems, optimizing the power consumption schedule, and reducing electricity and power costs. A comparative analysis of various algorithms for constructing decision tree ensembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features. The experiments demonstrated that using the developed method and production process factors reduced the MAE from 105.00 kWh (MAPE of 16.81%), obtained through expert forecasting, to 15.52 kWh (3.44%). Examples were provided of how the use of SHapley Additive exPlanation can increase the safety of the electrical system management of gas industry enterprises by improving experts’ confidence in the results of the information system.

An Adaptive Transfer Learning Framework for Data-Scarce HVAC Power Consumption Forecasting

An Adaptive Transfer Learning Framework for Data-Scarce HVAC Power Consumption Forecasting

Short-term forecasting of consumption of the oil and gas enterprises using technological factors and Shapley additive explanations

RELEVANCE of the study lies in the development of system for the short-term forecasting of power consumption by the enterprise of the oil and gas industry with consideration of technological factors and interpretation of their influence on the result of the forecast.THE PURPOSE. To consider the problems of short-term forecasting. To test the applicability of the multi-agent approach to determine the features used to build a machine learning model of short-term forecasting of power consumption. To build machine learning models. To study the influence of technological factors on the accuracy of forecasting of power consumption. To apply the SHapley Additive exPlanations and analyze its interpretation of the forecasting results.METHODS. Pre-processing of the dataset, construction and testing of machine learning models were made in the programming language Python 3 using opensource libraries Scikit-Learn, XGBoost, LightGBM, Shap.RESULTS. The article describes the relevance of the topic of short-term forecasting of power consumption by the enterprise of the oil and gas industry within the ESG-approach. The method of selecting the features used using a multi-agent approach to build a machine learning model was developed. Machine learning models were built. Experimentations with the consideration of different features were made. Interpretation of results using SHapley Additive exPlanations was made.CONCLUSION. The use of technological factors of power consumption of compressor yards and natural gas air coolers allowed to increase the accuracy of forecast of power consumption from 8.82 % to 3.65 %. The application of the SHapley Additive exPlanations allows to interpret the results of machine learning models and confirms the need to consider technological factors in the task of short-term forecasting of power consumption of oil and gas industry.

Seasonal Electrical Load Forecasting Using Machine Learning Techniques and Meteorological Variables

Accurate forecasting of seasonal power consumption is crucial for effective grid management, especially with increasing energy demand and renewable energy integration. Weather patterns significantly influence energy usage, making load prediction a challenging task. This study employs machine learning algorithms, including Random Forest (RF), Artificial Neural Networks (ANN), and Decision Tree (DT) models, to forecast electricity consumption using meteorological variables such as solar irradiance, humidity, and ambient temperature. The impact of weather elements on load prediction accuracy across different seasons is explored using seasonal forecasting techniques. The results demonstrate the superior performance of ANN and RF models in forecasting summer and winter loads compared to the rainy season. This discrepancy is attributed to the abundance of data for the summer and winter seasons, and the ability of the models to capture complex patterns within the data for these particular seasons. The study highlights the potential of machine learning techniques, particularly ANN and RF, in conjunction with meteorological data analysis, for enhancing the accuracy of seasonal electrical load forecasting. This can contribute to more effective power grid management and support the transition towards a more sustainable energy landscape. The findings underscore the importance of data quality, quantity, and appropriate model selection for different seasonal conditions.

A Trapezoid Attention Mechanism for Power Generation and Consumption Forecasting

A Trapezoid Attention Mechanism for Power Generation and Consumption Forecasting

Load Balance Forecasting Based on Hybrid Deep Neural Network

Load forecasting is the foundation of utility design, and it is a fundamental business problem in the utility industry. Load forecasting, mainly referring to forecasting electricity demand and energy, is being used throughout all segments of the electric power industry, including generation, transmission, distribution, and retail. In this paper, a long short-term memory network with a hybrid approach is improved with a dense algorithm and proposed for electricity load forecasting. A long short-term memory network is designed to effectively exhibit the dynamic behavior of load time series. The proposed model is tested for Panama study including historical data and weather variables. The prediction accuracy is validated by performance metrics, and the best of the metrics are attained when mean absolute error is 5.262, mean absolute percentage error 0.0000376, and root mean square error 18.243. The experimental results show a high prediction rate for load balance forecasting of electric power consumption.

Power consumption prediction for electric vehicle charging stations and forecasting income

Electric vehicles (EVs) are the future of the automobile industry, as they produce zero emissions and address environmental and health concerns caused by traditional fuel-poared vehicles. As more people shift towards EVs, the demand for power consumption forecasting is increasing to manage the charging stations effectively. Predicting power consumption can help optimize operations, prevent grid overloading, and power outages, and assist companies in estimating the number of charging stations required to meet demand. The paper uses three time series models to predict the electricity demand for charging stations, and the SARIMA (Seasonal Auto Regressive Integrated Moving Average) model outperforms the ARMA (Auto Regressive Moving Average) and ARIMA (Auto Regressive Integrated Moving Average) models, with the least RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error) scores in forecasting power demand and revenue. The data used for validation consists of charging activities over a four-year period from public charging outlets in Colorado, six months of charging data from ChargeMOD's public charging terminals in Kerala, India. Power usage is also forecasted based on wheels of vehicles, and finally, a plan subscription data from the same source is utilized to anticipate income, that helps companies develop pricing strategies to maximize profits while remaining competitive. Utility firms and charging networks may use accurate power consumption forecasts for a variety of purposes, such as power scheduling and determining the expected energy requirements for charging stations. Ultimately, precise power consumption forecasting can assist in the effective planning and design of EV charging infrastructure. The main aim of this study is to create a good time series model which can estimate the electric vehicle charging stations usage of power and verify if the firm has a good income along with some accuracy measures. The results show that SARIMA model plays a vital role in providing us with accurate information. According to the data and study here, four wheelers use more power than two and three wheelers. Also, DC charging facility uses more electricity than AC charging stations. These results can be used to determine the cost to operate the EVs and its subscriptions.

DBSCAN-based energy users clustering for performance enhancement of deep learning model

Background: Due to rapid progress in the fields of artificial intelligence, machine learning and deep learning, the power grids are transforming into Smart Grids (SG) which are versatile, reliable, intelligent and stable. The power consumption of the energy users is varying throughout the day as well as in different days of the week. Power consumption forecasting is of vital importance for the sustainable management and operation of SG. Methodology: In this work, the aim is to apply clustering for dividing a smart residential community into several group of similar profile energy user, which will be effective for developing and training representative deep neural network (DNN) models for power load forecasting of users in respective groups. The DNN models is composed of convolutional neural network (CNN) followed by LSTM layers for feature extraction and sequence learning respectively. The DNN For experimentation, the Smart Grid Smart City (SGSC) project database is used and its energy users are grouped into various clusters. Results: The residential community is divided into four groups of customers based on the chosen criterion where Group 1, 2, 3 and 4 contains 14 percent, 22 percent, 19 percent and 45 percent users respectively. Almost half of the population (45 percent) of the considered residential community exhibits less than 23 outliers in their electricity consumption patterns. The rest of the population is divided into three groups, where specialized deep learning models developed and trained for respective groups are able to achieve higher forecasting accuracy. The results of our proposed approach will assist researchers and utility companies by requiring fewer specialized deep-learning models for accurate forecasting of users who belong to various groups of similar-profile energy consumption.

Cognitive Modelling and Forecasting of Electricity Consumption

Purpose of reseach. Development of a forecast model of energy consumption and assessment of factors influencing its consumption. The obtained forecast estimates of energy consumption will improve the quality and efficiency of management decisions at all levels of administrative management.Methods. The article presents an analytical review of the existing methods of cognitive modelling and forecasting of electric power consumption, the description of the software implementation of the information-computing system that allows to make a forecast of electric power consumption by the population of the administrative-territorial formation. The approach to the description of factors of electric power consumption by both population and various branches of national economy, as well as organisations engaged in rendering various services has been proposed. Special software has been developed, which allows to obtain model results of electric power consumption in an automated mode, to carry out factor analysis of power consumption. The experimental verification of the work of the programme of cognitive modelling and forecasting of electric power consumption by the population of Lgovsky district of Kursk region is given. The developed software also makes it possible to evaluate the adequacy of the obtained results and promptly adjust the model parameters.Results. As a result of the research a fuzzy cognitive map of energy consumption for a municipal entity was developed. The concepts of the subject area describing the influence of various groups of factors on the level of electric energy consumption were identified. Forecast estimates of electricity consumption were obtained, which were based on the data for the retrospective period. Adequacy indicators based on the calculation of statistical criteria are determined for the obtained estimates.Conclusion. The results of the study have shown that the combination of cognitive and statistical methods allows to achieve an adequate solution when solving the problem of energy consumption forecasting.

A Novel Deep Learning‐Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid

With the installation of solar panels around the world and the permanent fluctuation of climatic factors, it is, therefore, important to provide the necessary energy in the electrical network in order to satisfy the electrical demand at all times for smart grid applications. This study first presents a comprehensive and comparative review of existing deep learning methods used for smart grid applications such as solar photovoltaic (PV) generation forecasting and power consumption forecasting. In this work, electrical consumption forecasting is long term and will consider smart meter data and socioeconomic and demographic data. Photovoltaic power generation forecasting is short term by considering climatic data such as solar irradiance, temperature, and humidity. Moreover, we have proposed a novel hybrid deep learning method based on multilayer perceptron (MLP), long short‐term memory (LSTM), and genetic algorithm (GA). We then simulated all the deep learning methods on a climate and electricity consumption dataset for the city of Douala. Electrical consumption data are collected from smart meters installed at consumers in Douala. Climate data are collected at the climate management center in the city of Douala. The results obtained show the outperformance of the proposed optimized method based on deep learning in the both electrical consumption and PV power generation forecasting and its superiority compared to basic methods of deep learning such as support vector machine (SVM), MLP, recurrent neural network (RNN), and random forest algorithm (RFA).

A Prediction Model of Power Consumption in Smart City Using Hybrid Deep Learning Algorithm

A smart city utilizes vast data collected through electronic methods, such as sensors and cameras, to improve daily life by managing resources and providing services. Moving towards a smart grid is a step in realizing this concept. The proliferation of smart grids and the concomitant progress made in the development of measuring infrastructure have garnered considerable interest in short-term power consumption forecasting. In reality, predicting future power demands has shown to be a crucial factor in preventing energy waste and developing successful power management techniques. In addition, historical time series data on energy consumption may be considered necessary to derive all relevant knowledge and estimate future use. This research paper aims to construct and compare with original deep learning algorithms for forecasting power consumption over time. The proposed model, LSTM-GRU-PPCM, combines the Long -Short-Term -Memory (LSTM) and Gated- Recurrent- Unit (GRU) Prediction Power Consumption Model. Power consumption data will be utilized as the time series dataset, and predictions will be generated using the developed model. This research avoids consumption peaks by using the proposed LSTM-GRU-PPCM neural network to forecast future load demand. In order to conduct a thorough assessment of the method, a series of experiments were carried out using actual power consumption data from various cities in India. The experiment results show that the LSTM-GRU-PPCM model improves the original LSTM forecasting algorithms evaluated by Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for various time series. The proposed model achieved a minimum error prediction of MAE=0.004 and RMSE=0.032, which are excellent values compared to the original LSTM. Significant implications for power quality management and equipment maintenance may be expected from the LSTM-GRU-PPCM approach, as its forecasts will allow for proactive decision-making and lead to load shedding when power consumption exceeds the allowed level

A Prediction Model of Power Consumption in Smart City Using Hybrid Deep Learning Algorithm

A smart city utilizes vast data collected through electronic methods, such as sensors and cameras, to improve daily life by managing resources and providing services. Moving towards a smart grid is a step in realizing this concept. The proliferation of smart grids and the concomitant progress made in the development of measuring infrastructure have garnered considerable interest in short-term power consumption forecasting. In reality, predicting future power demands has shown to be a crucial factor in preventing energy waste and developing successful power management techniques. In addition, historical time series data on energy consumption may be considered necessary to derive all relevant knowledge and estimate future use. This research paper aims to construct and compare with original deep learning algorithms for forecasting power consumption over time. The proposed model, LSTM-GRU-PPCM, combines the Long -Short-Term -Memory (LSTM) and Gated- Recurrent- Unit (GRU) Prediction Power Consumption Model. Power consumption data will be utilized as the time series dataset, and predictions will be generated using the developed model. This research avoids consumption peaks by using the proposed LSTM-GRU-PPCM neural network to forecast future load demand. In order to conduct a thorough assessment of the method, a series of experiments were carried out using actual power consumption data from various cities in India. The experiment results show that the LSTM-GRU-PPCM model improves the original LSTM forecasting algorithms evaluated by Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for various time series. The proposed model achieved a minimum error prediction of MAE=0.004 and RMSE=0.032, which are excellent values compared to the original LSTM. Significant implications for power quality management and equipment maintenance may be expected from the LSTM-GRU-PPCM approach, as its forecasts will allow for proactive decision-making and lead to load shedding when power consumption exceeds the allowed level

Multi-Task Learning and Temporal-Fusion-Transformer-Based Forecasting of Building Power Consumption

Improving the accuracy of the forecasting of building power consumption is helpful in reducing commercial expenses and carbon emissions. However, challenges such as the shortage of training data and the absence of efficient models are the main obstacles in this field. To address these issues, this work introduces a model named MTLTFT, combining multi-task learning (MTL) with the temporal fusion transformer (TFT). The MTL approach is utilized to maximize the effectiveness of the limited data by introducing multiple related forecasting tasks. This method enhances the learning process by enabling the model to learn shared representations across different tasks, although the physical number of data remains unchanged. The TFT component, which is optimized for feature learning, is integrated to further improve the model’s performance. Based on a dataset from a large exposition building in Hangzhou, we conducted several forecasting experiments. The results demonstrate that MTLTFT outperforms most baseline methods (such as LSTM, GRU, N-HiTS) in terms of Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), suggesting that MTLTFT is a promising approach for the forecasting of building power consumption and other similar tasks.

SAC-ConvLSTM: A novel spatio-temporal deep learning-based approach for a short term power load forecasting

The short-term spatiotemporal load forecasting of power distribution networks has been extensively studied in light of high importance in distribution system control and consumption management. Load forecasting is dependent on temporal and spatial parameters e.g., temperature, rainfall, and land use. Additionally, load time series have spatial autocorrelation in cities. Deep learning has been recently demonstrated to be effective and efficient in time-series and load forecasting in power distribution networks. The present study proposes a new algorithm based on Spatial Auto Correlation and Convolutional Long Short-Term Memory (SAC-ConvLSTM) algorithm via spatiotemporal power load autocorrelation modeling and deep learning. Load time-series signals in a power distribution network are decomposed into sub-signals using the discrete wavelet transform (DWT). Then, the spatio-temporal autocorrelation of sub-signals is calculated, alleviating prediction model complexity using spatial statistics. The areas with significant positive/negative/no significant autocorrelation in each time-series sub-signal are separately used as the input of the SAC-ConvLSTM algorithm. Finally, the sub-signals are reconstructed into the load signals. This algorithm models the spatial relationships in time-series at different time intervals for power consumption forecasting. The proposed methodology was found to outperform the support vector machine (SVM), Long Short Term Memory (LSTM), Convolutional LSTM (ConvLSTM), Convolutional Gated Recurrent Unit (ConvGRU), Planar Flow-Based Variational Auto-Encoder (PFVAE) and Federated Averaging (FedAVG) algorithms in short-term power load forecasting for short term forecasting of up to two weeks, based on the evaluation metrics of root-mean-square error (RMSE) and mean absolute error (MAE), producing values of 11.08% and 7.02% respectively.

Deep Learning Model Performance and Optimal Model Study for Hourly Fine Power Consumption Prediction

Electricity consumption has been increasing steadily owing to technological developments since the Industrial Revolution. Technologies that can predict power usage and management for improved efficiency are thus emerging. Detailed energy management requires precise power consumption forecasting. Deep learning technologies have been widely used recently to achieve high performance. Many deep learning technologies are focused on accuracy, but they do not involve detailed time-based usage prediction research. In addition, detailed power prediction models should consider computing power, such as that of end Internet of Things devices and end home AMIs. In this work, we conducted experiments to predict hourly demands for the temporal neural network (TCN) and transformer models, as well as artificial neural network, long short-term memory (LSTM), and gated recurrent unit models. The study covered detailed time intervals from 1 to 24 h with 1 h increments. The experimental results were analyzed, and the optimal models for different time intervals and datasets were derived. The LSTM model showed superior performance for datasets with characteristics similar to those of schools, while the TCN model performed better for average or industrial power consumption datasets.

Forecasting of short term electric power consumption for different types buildings using improved transfer learning: A case study of primary school in China

Accurate forecasting of electric power consumption is of great significance to the energy saving operation of buildings. However, in practice, few reliable historical data to be employed to forecast the electric power consumption of a building due to the non-availability of a complete system for monitoring of its energy consumption. In order to accurately predict the electric power consumption of a building with a small-size historical data sample, a model is proposed for forecasting daily electric power consumption using TrAdaBoost- Long short term memory (TAB-LSTM). Some new data is collected from the source building with the maximum mean dispersion (MMD), which is combined with the targeted data of the building to generate a training set. The weight of the training set is updated iteratively by transfer learning (TL) and LSTM to predict the daily electric power consumption. This approach is applied to the energy consumption data of a primary school located in the Northwest China. The experimental results show that the proposed TAB-LSTM approach could reduce the average error to 7.8%, and hence it can be used as an efficient tool for intelligent operation and maintenance of existing buildings.

Day-ahead forecasting of residential electric power consumption for energy management using Long Short-Term Memory encoder–decoder model

Energy management in smart buildings and energy communities needs short-term load demand forecasting for optimization-based scheduling, dispatch, and real-time operation. However, producing accurate forecasting for individual residential households is more challenging compared to the forecasting of load demand at the distribution level, which is smoother and benefits from statistical compensation of errors. This paper presents a day-ahead forecasting technique for individual residential load demand that is based on the Long Short-Term Memory encoder–decoder architecture, which is extended to consider possibly differing sets of past and future exogenous variables. A novel focus is posed on the validation of the proposed approach considering that it is tailored for use by energy management systems. A publicly available dataset was used for validation, and the approach was compared with three other methods, resulting in a reduction of the Mean Absolute Scaled Error by up to 8%.

Data-Driven Insights through Industrial Retrofitting: An Anonymized Dataset with Machine Learning Use Cases

Small and medium-sized enterprises (SMEs) often encounter practical challenges and limitations when extracting valuable insights from the data of retrofitted or brownfield equipment. The existing literature fails to reflect the full reality and potential of data-driven analysis in current SME environments. In this paper, we provide an anonymized dataset obtained from two medium-sized companies leveraging a non-invasive and scalable data-collection procedure. The dataset comprises mainly power consumption machine data collected over a period of 7 months and 1 year from two medium-sized companies. Using this dataset, we demonstrate how machine learning (ML) techniques can enable SMEs to extract useful information even in the short term, even from a small variety of data types. We develop several ML models to address various tasks, such as power consumption forecasting, item classification, next machine state prediction, and item production count forecasting. By providing this anonymized dataset and showcasing its application through various ML use cases, our paper aims to provide practical insights for SMEs seeking to leverage ML techniques with their limited data resources. The findings contribute to a better understanding of how ML can be effectively utilized in extracting actionable insights from limited datasets, offering valuable implications for SMEs in practical settings.