Electricity Demand Prediction Research Articles

Modelling and Analysis of Future Energy Scenarios on the Sustainability Axis

This study aims to propose a sustainable electricity mix option for Turkey by 2030. First, the electricity demand of Turkey by 2030 is estimated by employing a method that comprises MLP ANN and GPRM. Population, GDP, imports, exports, and IPI are considered independent variables used in the ANN model. The future values of each of the independent variables are predicted by a GPRM model based on a univariate time series approach. ANN model is then employed to predict electricity demand based on the future values of independent variables. Secondly, four diverse electricity mix scenarios are developed considering the forecasted electricity demand. The sustainability evaluation of the scenarios is performed using TOPSIS method considering ten different criteria classified into environmental, economic, technical, and social categories. Furthermore, four diverse weight sets are determined for the given categories, and also a sensitivity analysis is carried out. Turkey’s electricity demand is found out as ≈ 384,569 GWh according to the prediction for the year 2030. The Scenario-(C), which has a comparatively higher percent of nuclear energy generation, is determined as the most sustainable electricity mix scenario according to evaluation with the TOPSIS method.

A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction

A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction

FORECASTING ELECTRICITY DEMAND WITH FORECASTERAUTOREG: CASE STUDY IN ASTANA

This paper presents the application of time series forecasting models, namely Forecaster Autoreg and Neural Network, for predicting electricity consumption in the city of Astana. Given the pressing need to address energy efficiency and reduce environmental impact in light of global climate change, employing scientifically sound and effective solutions is crucial. Machine learning methods offer a promising approach to tackle this challenge by predicting electricity demand. In this study, a comprehensive analysis of a time series dataset was conducted, encompassing data on electricity consumption (measured in MW) in Astana from January 1, 2020, to December 31, 2020, at an hourly interval. The dataset was utilized to accurately forecast electricity demand for each hour of the following day. To enhance the precision of predictions, additional factors such as air temperature and wind speed were incorporated. These factors were deemed significant due to Astana’s distinct sharply continental climate and high windiness, making their inclusion essential for accounting for their influence on electricity demand and achieving more accurate forecasts. The neural network model was selected as the chosen methodology, as it has the capability to reveal intricate dependencies and patterns in the data, thereby facilitating more precise predictions of electricity consumption. To evaluate the accuracy and reliability of the forecasts, error indicators such as Average Absolute Error (MAE) and Average Absolute Percentage Error (MAPE) were employed. The results demonstrated that the proposed models could provide accurate forecasts with low errors.

A machine learning approach for time series forecasting with application to debt risk of the Montenegrin electricity industry

Level of customer electricity debts is a relevant information for the electricity production company, as it represents uncollected revenue for the provided service. Higher level of debts may affect the provider’s financial stability and the ability to invest and maintain their network. On the other hand, high levels of debt may indicate larger macroeconomic problems, such as the lower standard of the citizens or high unemployment. In this paper, a Machine Learning approach for electricity debt prediction was applied, using Support Vector Regression method and data from the Montenegrin electricity provider. The obtained results indicate an excellent model performance, proving that the chosen method is an outstanding choice for this task, compared to other machine learning methods. The forecast of electricity user debts using machine learning techniques adds a new research area to the existing research, as the previous literature mostly concentrated on the prediction of electric load, consumption, and demand. The risk of default may be larger in lower income nations, as is the case in this research, therefore risk prediction and mitigation are crucial for the power supplier in these countries. The results obtained in this research on the test set are 1.63% and 0.854, for Relative Error and R2, respectively, showing excellent predictive performance. Additionally, correlation coefficient is close to 1 in cross-validation and on unknown data. Thus, it can be confirmed that the debt prediction was efficient.

Tree-based boosting with functional data

In this article we propose a boosting algorithm for regression with functional explanatory variables and scalar responses. The algorithm uses decision trees constructed with multiple projections as the “base-learners”, which we call “functional multi-index trees”. We establish identifiability conditions for these trees and introduce two algorithms to compute them. We use numerical experiments to investigate the performance of our method and compare it with several linear and nonlinear regression estimators, including recently proposed nonparametric and semiparametric functional additive estimators. Simulation studies show that the proposed method is consistently among the top performers, whereas the performance of existing alternatives can vary substantially across different settings. In a real example, we apply our method to predict electricity demand using price curves and show that our estimator provides better predictions compared to its competitors, especially when one adjusts for seasonality.

Multi-region electricity demand prediction with ensemble deep neural networks.

Electricity consumption prediction plays a vital role in intelligent energy management systems, and it is essential for electricity power supply companies to have accurate short and long-term energy predictions. In this study, a deep-ensembled neural network was used to anticipate hourly power utilization, providing a clear and effective approach for predicting power consumption. The dataset comprises of 13 files, each representing a different region, and ranges from 2004 to 2018, with two columns for the date, time, year and energy expenditure. The data was normalized using minmax scalar, and a deep ensembled (long short-term memory and recurrent neural network) model was used for energy consumption prediction. This proposed model effectively trains long-term dependencies in sequence order and has been assessed using several statistical metrics, including root mean squared error (RMSE), relative root mean squared error (rRMSE), mean absolute bias error (MABE), coefficient of determination (R2), mean bias error (MBE), and mean absolute percentage error (MAPE). Results show that the proposed model performs exceptionally well compared to existing models, indicating its effectiveness in accurately predicting energy consumption.

Analyzing the impact of COVID-19 on the electricity demand in Austin, TX using an ensemble-model based counterfactual and 400,000 smart meters

The COVID-19 pandemic caused lifestyle changes and has led to the new electricity demand patterns in the presence of non-pharmaceutical interventions such as work-from-home policy and lockdown. Quantifying the effect on electricity demand is critical for future electricity market planning yet challenging in the context of limited smart metered buildings, which leads to limited understanding of the temporal and spatial variations in building energy use. This study uses a large scale private smart meter electricity demand data from the City of Austin, combined with publicly available environmental data, and develops an ensemble regression model for long term daily electricity demand prediction. Using 15-min resolution data from over 400,000 smart meters from 2018 to 2020 aggregated by building type and zip code, our proposed model precisely formalizes the counterfactual universe in the without COVID-19 scenario. The model is used to understand building electricity demand changes during the pandemic and to identify relationships between such changes and socioeconomic patterns. Results indicate the increase in residential usage , demonstrating the spatial redistribution of energy consumption during the work-from-home period. Our experiments demonstrate the effectiveness of our proposed framework by assessing multiple socioeconomic impacts with the comparison between the counterfactual universe and observations.

Short-term electric vehicle battery swapping demand prediction: Deep learning methods

Battery swap stations have become an important alternative to general charging posts. Predicting battery swapping demand at the station level would be helpful for real-time operation of stations. This paper first provided insights into battery swapping demand patterns by analyzing a real-world dataset which contained 2,529 battery swapping events collected from 36 battery swap stations in Beijing from 31st July to 20th August 2019. Further, we developed a series of deep learning methods to predict the EV battery swapping demand, particularly considering temporal demand patterns obtained from the dataset. The deep learning models were Long Short-Term Memory, Bidirectional Long Short-Term Memory, Gated Recurrent Units, and Bidirectional Gated Recurrent Units. The results showed that the four deep learning models outperformed typical machine learning methods (e.g., support vector regression). An ablation study indicated that incorporating temporal battery swapping demand patterns into the deep learning methods could greatly improve model performance.

Short-term power forecasting model based on GWO-LSTM network

In view of the time-series characteristics of the grid load data, this paper proposes a method to predict electricity demand by optimizing a long-and short-term memory (LSTM) neural network model using the grey wolf optimization algorithm, taking into account the effects of time, weather conditions and holiday conditions on electricity loads. The model overcomes the disadvantage that the backpropagation through the time algorithm tends to converge to a local optimum. The experimental results show that the prediction results outperform those of the traditional LSTM for short-term electricity loads, providing a reference direction for future electricity forecasting models.

Deep learning hyperparameter optimization: Application to electricity and heat demand prediction for buildings

Optimal planning and operation studies of modern energy systems are tied up with medium to long-term predictions of energy demand. Deep learning algorithms have recently become significantly useful in this regard because of their capacity to learn load patterns with a high degree of fluctuation and uncertainty. Yet, empirical evaluation of different configurations of deep learning models, for enhancing prediction accuracy, has been mostly ignored in the preceding literature. In this paper, different architectures of deep recurrent neural networks (DRNNs) are explored and adjusted specifically for the purpose of performing medium- and long-term predictions of energy demands. We intend to create a bespoke DRNN for heating and electricity consumption prediction with a 1-h resolution. Moreover, hyperparameter optimization, which is a time-consuming and rigorous task in deep learning algorithms due to their abundance, dependence on the particular application, and empirical nature, is studied comprehensively. In this respect, the space of possible configuration variables is thoroughly explored to identify a collection of hyperparameters that enables the DRNN model to more accurately forecast energy consumption. We also benchmark the proposed algorithm’s performance against other data-driven models, namely support vector machine (SVM) and gradient boosting (GB) regression. The proposed model outperforms SVM by 5.4% and GB regression by 7.0% in terms of energy forecasting accuracy.

Short-term electric vehicle charging demand prediction: A deep learning approach

Short-term prediction of the Electric Vehicle (EV) charging demand is of great importance to the operation of EV fleets and charging stations. This paper develops a Long Short-Term Memory (LSTM) neural network to predict the EV charging demand at the station level for the next few hours (e.g., 1–5 h), using a unique trajectory dataset containing over 76,000 private EVs in Beijing in January 2018. To explore the performance of the LSTM model, we set up four scenarios by 1) comparing LSTM against two typical time series prediction models, i.e., the Auto-Regressive Moving Average model (ARIMA), and the Multiple Layer Perceptron model (MLP), 2) and investigating how different input data structures, sample sizes, and time spans and intervals would influence model accuracy. The results suggest that the LSTM model outperformed the ARIMA, and MLP models, and their MAPE1 values are 6.83 %, 21.58 %, and 18.31 %, respectively. In addition, we find that the time span and interval tend to be more influential to the LSTM model’s prediction accuracy than input data structures, and sample sizes. In general, the LSTM model with a shorter time span or interval (e.g., 1 h) would perform better.

Predicting the short-term electricity demand based on the weather variables using a hybrid CatBoost-PPSO model

In this study, by using the capabilities of the CatBoost model and meta-heuristic algorithms, as well as the hybridization technique, an attempt was made to improve the prediction of electricity demand on a short-term scale. For this purpose, the hybrid CatBoost-PPSO model was suggested in this study to predict electricity demand based on weather variables. Finally, by conducting a case study and comparing the results of the proposed model with five other hybrid models, the results were evaluated and compared using various statistical indexes. The general approach used in this study is that the hyper-parameters of the Catboost were optimized using a meta-heuristic algorithm, and the best of them were used during the forecasting process. Also, during the network training, the K-Fold cross-validation algorithm is used to avoid over-fitting. The evaluation results of the models based on the test data showed that the hybrid CatBoost-PPSO model has high capabilities in short-term electricity demand forecasting. The indices obtained from this model show better values than other hybrid models. For example, the RMSE value of this model is equal to 42.3, which shows an improvement of almost 9.5% compared to the hybrid CatBoost-ALO model.

Secure-Enhanced Federated Learning for AI-Empowered Electric Vehicle Energy Prediction

Although AI-empowered schemes bring some sound solutions to stimulate more reasonable energy distribution schemes between charging stations (CSs) and CS providers, frequent data sharing between them is possible to incur many security and privacy breaches. To solve these problems, federated learning (FL) is an ideal solution that only requires CSs to upload local models instead of detailed data. Although the CSs’ electricity consumption need not to be exposed to the server directly, FL-based schemes still have been excavated several security threats such as information exploiting attacks, data poisoning attacks, model poisoning attacks, and free-riding attacks. Hence, in this article, both the effectiveness of energy management and the potential risks of FL for electric vehicle infrastructures (EVIs) are considered, we propose a lightweight authentication FL-based energy demand prediction for EVIs with premium-penalty mechanism. Security analysis and performance evaluation prove that our proposed framework can generate an accurate electricity demand prediction framework to defend multiple FL attacks for EVIs.

Predicting smart cities’ electricity demands using k-means clustering algorithm in smart grid

This work aims to perform the unified management of various departments engaged in smart city construction by big data, establish a synthetic data collection and sharing system, and provide fast and convenient big data services for smart applications in various fields. A new electricity demand prediction model based on back propagation neural network (BPNN) is proposed for China?s electricity industry according to the smart city?s big data characteristics. This model integrates meteorological, geographic, demographic, corporate, and economic information to form a big intelligent database. Moreover, the K-means clustering algorithm mines and analyzes the data to optimize the power consumers? information. The BPNN model is used to extract features for prediction. Users with weak daily correlation obtained by the K-means clustering algorithm only input the historical load of adjacent moments into the BPNN model for prediction. Finally, the electricity market is evaluated by exploring the data correlation in-depth to verify the proposed model?s effectiveness. The results indicate that the K-mean algorithm can significantly improve the segmentation accuracy of power consumers, with a maximum accuracy of 85.25% and average accuracy of 83.72%. The electricity consumption of different regions is separated, and the electricity consumption is classified. The electricity demand prediction model can enhance prediction accuracy, with an average error rate of 3.27%. The model?s training significantly speeds up by adding the momentum factor, and the average error rate is 2.13%. Therefore, the electricity demand prediction model achieves high accuracy and training efficiency. The findings can provide a theoretical and practical foundation for electricity demand prediction, personalized marketing, and the development planning of the power industry.

Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features. Electric kickboards are gradually growing in popularity in tourist and education-centric localities. In the upcoming arrival of electric kickboard vehicles, deploying a customer rental service is essential. Due to its free-floating nature, the shared electric kickboard is a common and practical means of transportation. Relocation plans for shared electric kickboards are required to increase the quality of service, and forecasting demand for their use in a specific region is crucial. Predicting demand accurately with small data is troublesome. Extensive data is necessary for training machine learning algorithms for effective prediction. Data generation is a method for expanding the amount of data that will be further accessible for training. In this work, we proposed a model that takes time-series customers’ electric kickboard demand data as input, pre-processes it, and generates synthetic data according to the original data distribution using generative adversarial networks (GAN). The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data. We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results. We modified The Wasserstein GAN-gradient penalty (GP) with the RMSprop optimizer and then employed Spectral Normalization (SN) to improve training stability and faster convergence. Finally, we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction. We used various evaluation criteria and visual representations to compare our proposed model’s performance. Synthetic data generated by our suggested GAN model is also evaluated. The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem, and it also converges faster than previous GAN models for synthetic data creation. The presented model’s performance is compared to existing ensemble and baseline models. The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error (MAPE) of 4.476 and increase prediction accuracy.

An exposition on the prediction of load on a Smart Grid

Smart grids depend on AI-based load forecasting to estimate future power demand (AI). Deep learning is especially important in smart grid load forecasting with neural networks (ANN). Processing time and data are needed to count smart grid deep learning. Combining data would speed load projections. The bottleneck strategy has been abandoned to attain this precision. Keeping the lights on requires short-term electricity demand prediction. But, the load’s intricacy and volatility make it fun to predict. EEMD breaks the load into many frequency-dependent components of different strengths. MLR predicts low-frequency regularities, while LSTM neural networks predict high-frequency components. Computational extent is unchanged. Despite its varied aggregation scope, the electric grid’s large data can be used to create the most effective deep learning models for Short-term Load Forecasting (STLF) in electrical networks. Hence, a suitable forecasting strategy uses deep learning with a Micro-clustering (MC) job that mixes unsupervised and supervised clustering tasks utilizingKmeans and Gaussian Support Vector Machine. To guarantee accuracy. B-bidirectional LSTMs can store feed-forward and future hidden-layer data. Feedback and feed-forward loops do this. The DaviesBouldering index determined cluster production per hour. MC with B-LSTM networks improves prediction,especially around spike locations. Forecasting RE generation and grid load is difficult. Prosumer microgrids (PMGs) sell electricity to aggregators. A hybrid machine learning-based load and weather data transmission method provides the biggest benefit. ANFIS, MLP, and radial basis function artificial neural networks (ANNs) would be used in this technique (RBF). Machine learning-based hybrid forecasting can improve accuracy.

Prediction of Electric Power Demand of HVACs for Operating Rooms in Case of Dynamic Set Points of Temperature: A Case Study

In healthcare settings, particularly in areas such as operating rooms and intensive care units, there is a need for a dynamically controlled temperature environment that can adapt to the changing needs of both patients and healthcare workers. This is due to the fact that the desired temperature can vary depending on the condition of the patient and the specific requirements of surgical and treatment procedures. To address this need, our objective is to develop a tool for predicting the electric power needed to maintain a desired temperature in these critical care areas. Previous research has employed artificial learning algorithms and mathematical equations to predict electric power for various types and sizes of buildings, with promising results. However, our study focuses specifically on critical care areas within hospitals and utilizes fluctuating temperature set-points to predict power demand using historical weather data and Building Management System (BMS) data. We employed both Multi-Layer Artificial Neural Network (ML-ANN) and Long short-term memory (LSTM) models for this purpose and found that ML-ANN outperformed LSTM. The results showed that the ML-ANN model performed better than the LSTM model, with a testing accuracy of 96% compared to 78% for the LSTM model. This indicates that the ML-ANN model was more accurate in predicting the power consumption for the desired temperature in the operating room.

An Adaptive Strategy for Medium-Term Electricity Consumption Forecasting for Highly Unpredictable Scenarios: Case Study Quito, Ecuador during the Two First Years of COVID-19

This research focuses its efforts on the prediction of medium-term electricity consumption for scenarios of highly variable electricity demand. Numerous approaches are used to predict electricity demand, among which the use of time series (ARMA, ARIMA) and the use of machine learning techniques, such as artificial neural networks, are the most covered in the literature review. All these approaches evaluate the prediction error when comparing the generated models with the data that fed the model, but they do not compare these values with the actual data of electricity demand once these are obtained, in addition, these techniques present high error values when there are unexpected changes in the trend of electricity consumption. This work proposes a methodology to generate an adaptive model for unexpected changes in electricity demand through the use of optimization in conjunction with SARIMA time series. The proposed case study is the electricity consumption in Quito, Ecuador to predict the electricity demand in the years 2019 and 2020, which are particularly challenging due to atypical electricity consumption attributed to COVID-19. The results show that the proposed model is capable of following the trend of electricity demand, adapting itself to sudden changes and obtaining an average error of 2.5% which is lower than the average error of 5.43% when using a non-adaptive approach (more than 50% or error improvement).

Electricity Consumption Prediction in an Electronic System Using Artificial Neural Networks

The tremendous rise of electrical energy demand worldwide has led to many problems related to efficient use of electrical energy, consequently posing difficult challenges to electricity consumers of all levels—from households to large companies’ facilities. Most of these challenges could be overcome by the accurate prediction of electricity demand. Additionally, balance responsibility includes the penalty-based financial mechanism causing extra expense for badly estimated consumption, above the allowed imbalance limits. In this paper, a method for electricity consumption prediction based on artificial neural networks is proposed. The electricity consumption dataset is obtained from a cold storage facility, which generates data in hourly intervals. The data obtained are measured for a period of over 2 years and then separated to four seasons, so different models are developed for each season. Five different network structures (ordinary RNN, LSTM, GRU, bidirectional LSTM, bidirectional GRU) for five different values of horizon, i.e., input data (one day, two days, four days, one week, two weeks) are examined. Performance indices, such as mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE) and mean square error (MSE), are used in order to obtain qualitative and quantitative comparisons among the obtained models. The results show that the modifications of recurrent neural networks perform much better than ordinary recurrent neural networks. GRU and LSTMB structures with horizons of 168h and 336h are found to have the best performances.

Regression model-based hourly aggregated electricity demand prediction

The ability to predict ggregated electricity demand of n electrical grid on an hourly basis is crucial for energy and demand management. In this study, demand and its categorical features data for three years are segregated into four seasons and then fed to an efficient Machine Learning Categorical Boosting (ML CatBoost) Regressor model to predict the next year’s demand. It uses a new gradient boosting algorithm that handles categorical features adeptly. Also, this model uses a new scheme for estimating leaf values while choosing tree structure which reduces overfitting. Further, hourly electricity demand data from the Electricity Reliability Council of Texas (ERCOT western) is used as the benchmark data to evaluate the CatBoost model. Moreover, five other ML models were developed, analyzed, and tested for the same ERCOT data for predicting the hourly aggregated electricity demand. The suggested model is compared with the long short-term memory neural network (LSTM-NN) and five other ML models in terms of performance evaluation matrices. Here, one additional performance evaluation parameter, the Coefficient of variation Root Mean Squared (CV-RMSE) is evaluated in addition to the benchmark paper’s parameters. In addition, the importance of accurate prediction in the electric grid for clean energy is discussed.