Short-term Electricity Demand Forecasting Research Articles

A Deep Learning Approach for Short-Term Electricity Demand Forecasting: Analysis of Thailand Data

Accurate electricity demand forecasting serves as a vital planning tool, enhancing the reliability of management decisions. Apart from that, achieving these aims, particularly in managing peak demand, faces challenges due to the industry’s volatility and the ongoing increase in residential energy use. Our research suggests that employing deep learning algorithms, such as recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), holds promise for the accurate forecasting of electrical energy demand in time series data. This paper presents the construction and testing of three deep learning models across three separate scenarios. Scenario 1 involves utilizing data from all-day demand. In Scenario 2, only weekday data are considered. Scenario 3 uses data from non-working days (Saturdays, Sundays, and holidays). The models underwent training and testing across a wide range of alternative hyperparameters to determine the optimal configuration. The proposed model’s validation involved utilizing a dataset comprising half-hourly electrical energy demand data spanning seven years from the Electricity Generating Authority of Thailand (EGAT). In terms of model performance, we determined that the RNN-GRU model performed better when the dataset was substantial, especially in scenarios 1 and 2. On the other hand, the RNN-LSTM model is excellent in Scenario 3. Specifically, the RNN-GRU model achieved an MAE (mean absolute error) of 214.79 MW and an MAPE (mean absolute percentage error) of 2.08% for Scenario 1, and an MAE of 181.63 MW and MAPE of 1.89% for Scenario 2. Conversely, the RNN-LSTM model obtained an MAE of 226.76 MW and an MAPE of 2.13% for Scenario 3. Furthermore, given the expanded dataset in Scenario 3, we can anticipate even higher precision in the results.

Electricity Demand Forecasting using LSTMs

Electricity demand forecasting is an essential task in the energy industry, enabling utilities and energy suppliers to optimize the generation, transmission, and distribution of electricity. In recent years, deep learning techniques such as Long Short -Term Memory (LSTM) neural networks have shown great potential in improving the accuracy and efficiency of time-series forecasting tasks, including electricity demand forecasting. This research proposes an LSTM-based neural network architecture for short-term electricity demand forecasting. The proposed model is evaluated on real-world electricity demand data, and the results demonstrate its effectiveness in predicting future demand patterns. The model's performance is evaluated using the Mean Squared Error loss function and the Root Mean Squared Error metric. The proposed model shows promising results compared to traditional time-series forecasting models. The results suggest that LSTM-based neural networks can be a powerful tool for electricity demand forecasting, providing more accurate and efficient forecasting models that can help improve energy system planning and decision making.

Probabilistic Forecasting of Electricity Demand Incorporating Mobility Data

Due to extreme weather conditions and anomalous events such as the COVID-19 pandemic, utilities and grid operators worldwide face unprecedented challenges. These unanticipated changes in trends introduce new uncertainties in conventional short-term electricity demand forecasting (EDF) since its result depends on recent usage as an input variable. In order to quantify the uncertainty of EDF effectively, this paper proposes a comprehensive probabilistic EFD method based on Gaussian process regression (GPR) and kernel density estimation (KDE). GPR is a non-parametric method based on Bayesian theory, which can handle the uncertainties in EDF using limited data. Mobility data is incorporated to manage uncertainty and pattern changes and increase forecasting model scalability. This study first performs a correlation study for feature selection that comprises weather, renewable and non-renewable energy, and mobility data. Then, different kernel functions of GPR are compared, and the optimal function is recommended for real applications. Finally, real data are used to validate the effectiveness of the proposed model and are elaborated with three scenarios. Comparison results with other conventional adopted methods show that the proposed method can achieve high forecasting accuracy with a minimum quantity of data while addressing forecasting uncertainty, thus improving decision-making.

Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review

In this paper, a systematic literature review is presented, through a survey of the main digital databases, regarding modelling methods for Short-Term Load Forecasting (STLF) for hourly electricity demand for residential electricity and to realize the performance evolution and impact of Artificial Intelligence (AI) in STLF. With these specific objectives, a conceptual framework on the subject was developed, along with a systematic review of the literature based on scientific publications with high impact and a bibliometric study directed towards the scientific production of AI and STLF. The review of research articles over a 10-year period, which took place between 2012 and 2022, used the Preferred Reporting Items for Systematic and Meta-Analyses (PRISMA) method. This research resulted in more than 300 articles, available in four databases: Web of Science, IEEE Xplore, Scopus, and Science Direct. The research was organized around three central themes, which were defined through the following keywords: STLF, Electricity, and Residential, along with their corresponding synonyms. In total, 334 research articles were analyzed, and the year of publication, journal, author, geography by continent and country, and the area of application were identified. Of the 335 documents found in the initial research and after applying the inclusion/exclusion criteria, which allowed delimiting the subject addressed in the topics of interest for analysis, 38 (thirty-eight) documents were in English (26 journal articles and 12 conference papers). The results point to a diversity of modelling techniques and associated algorithms. The corresponding performance was measured with different metrics and, therefore, cannot be compared directly. Hence, it is desirable to have a unified dataset, together with a set of benchmarks with well-defined metrics for a clear comparison of all the modelling techniques and the corresponding algorithms.

Research On The Daily Electricity Forecast Model Based On LightGBM

Short-term electricity demand forecast is of great significance for guiding the Power Grid Company production operation, but the existing forecast mainly concentrated on load forecast, and most of them only use meteorological and date factors as input features, ignoring the economic factors as a basis to support the growth of electricity, also doesn’t take into account the influence of recent significant events. To improve the accuracy and rationality of short-term electricity demand forecast, based on the Light Gradient Boosting Machine (LightGBM) model, in addition to the common meteorological and date factors, all kinds of economic and significant events are introduced into the model to forecast the daily electricity in this paper. The results show that economic and significant events provide useful information, making our model more accurate than previous short-term electricity demand forecasts. Moreover, due to the adoption of machine learning algorithms, our model is more stable and accurate than traditional measurement models with the same factors.

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.

A Review of Auto-Regressive Methods Applications to Short-Term Demand Forecasting in Power Systems

The paper conducts a literature review of applications of autoregressive methods to short-term forecasting of power demand. This need is dictated by the advancement of modern forecasting methods and their achievement in good forecasting efficiency in particular. The annual effectiveness of forecasting power demand for the Polish National Power Grid for the next day is approx. 1%; therefore, the main objective of the review is to verify whether it is possible to improve efficiency while maintaining the minimum financial outlays and time-consuming efforts. The methods that fulfil these conditions are autoregressive methods; therefore, the paper focuses on autoregressive methods, which are less time-consuming and, as a result, cheaper in development and applications. The prepared review ranks the forecasting models in terms of the forecasting effectiveness achieved in the literature on the subject, which enables the selection of models that may improve the currently achieved effectiveness of the transmission system operator. Due to the applied approach, a transparent set of forecasting methods and models was obtained, in addition to knowledge about their potential in the context of the needs for short-term forecasting of electricity demand in the national power system. The articles in which the MAPE error was used to assess the quality of short-term forecasts were analyzed. The investigation included 47 articles, several dozen forecasting methods, and 264 forecasting models. The articles date from 1997 and, apart from the autoregressive methods, also include the methods and models that use explanatory variables (non-autoregressive ones). The input data used come from the period 1998–2014. The analysis included 25 power systems located on four continents (Asia, Europe, North America, and Australia) that were published by 44 different research teams. The results of the review show that in the autoregressive methods applied to forecasting short-term power demand, there is a potential to improve forecasting effectiveness in power systems. The most promising prognostic models using the autoregressive approach, based on the review, include Fuzzy Logic, Artificial Neural Networks, Wavelet Artificial Neural Networks, Adaptive Neurofuse Inference Systems, Genetic Algorithms, Fuzzy Regression, and Data Envelope Analysis. These methods make it possible to achieve the efficiency of short-term forecasting of electricity demand with hourly resolution at the level below 1%, which confirms the assumption made by the authors about the potential of autoregressive methods. Other forecasting models, the effectiveness of which is high, may also prove useful in forecasting by electricity system operators. The paper also discusses the classical methods of Artificial Intelligence, Data Mining, Big Data, and the state of research in short-term power demand forecasting in power systems using autoregressive and non-autoregressive methods and models.

Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting

Short-term electricity demand forecasting is one of the best ways to understand the changing characteristics of demand that helps to make important decisions regarding load flow analysis, preventing imbalance in generation planning, demand management, and load scheduling, all of which are actions for the reliability and quality of that power system. The variation in electricity demand depends upon various parameters, such as the effect of the temperature, social activities, holidays, the working environment, and so on. The selection of improper forecasting methods and data can lead to huge variations and mislead the power system operators. This paper presents a study of electricity demand and its relation to the previous day’s lags and temperature by examining the case of a consumer distribution center in urban Nepal. The effect of the temperature on load, load variation on weekends and weekdays, and the effect of load lags on the load demand are thoroughly discussed. Based on the analysis conducted on the data, short-term load forecasting is conducted for weekdays and weekends by using the previous day’s demand and temperature data for the whole year. Using the conventional time series model as a benchmark, an ANN model is developed to track the effect of the temperature and similar day patterns. The results show that the time series models with feedforward neural networks (FF-ANNs), in terms of the mean absolute percentage error (MAPE), performed better by 0.34% on a weekday and by 8.04% on a weekend.

Deep reservoir architecture for short-term residential load forecasting: An online learning scheme for edge computing

The short-term residential electricity demand forecast tasks are essential for designing the portfolio of the decision-making process of aggregators for the selection of control targets and derivation of specific control target values for demand response. The implementation of edge computing on the forecast functionality, which provides forecasting and minimal communication functions based on the data accumulated at the end-user-side using an inexpensive computational resource deployed locally, is an attractive framework for practical implementation. To achieve good accuracy while forecasting the demands of individual households during practical long-term operation, it is necessary to follow the changes in demand characteristics quickly by updating the prediction models frequently. This study focused on the concept of deep reservoir computing, which has a high affinity for implementation in edge computing frameworks from the viewpoint of hardware implementability, while utilizing the deep architecture and avoiding high computational cost. In particular, this study proposed an online learning scheme for the implementation of edge computing, which does not require large-scale computation for updating the prediction models. The effectiveness of the proposed approach was evaluated considering the calculation cost and accuracy through numerical experiments using real-world residential load data.

Electricity demand forecasting in industrial and residential facilities using ensemble machine learning

This article presents electricity demand forecasting models for industrial and residential facilities, developed using ensemble machine learning strategies. Short term electricity demand forecasting is beneficial for both consumers and suppliers, as it allows improving energy efficiency policies and the rational use of resources. Computational intelligence models are developed for day-ahead electricity demand forecasting. An ensemble strategy is applied to build the day-ahead forecasting model based on several one-hour models. Three steps of data preprocessing are carried out, including treating missing values, removing outliers, and standardization. Feature extraction is performed to reduce overfitting, reducing the training time and improving the accuracy. The best model is optimized using grid search strategies on hyperparameter space. Then, an ensemble of 24 instances is generated to build the complete day-ahead forecasting model. Considering the computational complexity of the applied techniques, they are developed and evaluated on the National Supercomputing Center (Cluster-UY), Uruguay. Three different real data sets are used for evaluation: an industrial park in Burgos (Spain), the total electricity demand for Uruguay, and demand from a distribution substation in Montevideo (Uruguay). Standard performance metrics are applied to evaluate the proposed models. The main results indicate that the best day ahead model based on ExtraTreesRegressor has a mean absolute percentage error of 2:55% on industrial data, 5:17% on total consumption data and 9:09% on substation data.

A novel hybrid forecasting scheme for electricity demand time series

Electricity demand/load forecasting always plays a vital role in the management and operation of power systems, since it can help develop an optimal action program for power producers, end-consumers and government entities. Inaccurate prediction may cause an additional production or waste of resources due to high operational costs. This paper investigated the benefit of combining data features to produce short-term electricity demand forecast. The nature of the electricity usually presents the complex characteristic and obvious seasonal tendency. In this paper, the advantage of adaptive Fourier decomposition is firstly used to extract the fluctuation characteristics. Then, the condition of the linear and stationary sequence is satisfied and the sub-series are performed to measure and eliminate the seasonal pattern. In the process of seasonal adjustment, the average periodicity length is identified quantitatively. In addition, to realize the generalization performance on real electricity demand data, the sine cosine optimization algorithm is applied to select the penalty and kernel parameters of support vector machine. The empirical study showed that the superior property of the proposed hybrid method profits from the effect of data pretreatment and the findings prove that this hybrid modeling scheme can yield promising prediction results within acceptable computational complexity.

Improvement of performance of short term electricity demand model with meteorological parameters

The accuracy of short term electricity demand forecasting is essential for operation and trading activities on energy market. This paper considers a parsimonious forecasting model to explain the importance of sophisticated weather parameters for hourly electricity demand forecasting. Temperature is the major factor that directly influence electricity demand, but what about the affect of other weather factors such as relative humidity, wind speed etc. on short term electricity demand forecasting, is the prime research question and this paper analyzed it quantitatively. We demonstrate three different multiple linear models including auto-regressive moving average ARMA (2,6) models with and without some exogenous weather variables to compare with performance for Hokkaido Prefecture, Japan. Since, Bayesian approach is used to estimate the weight of each variables with Gibbs sampling, it generates the weight of coefficients in terms of distribution as our interest. The performance of each models for complete one year out sample prediction shows that the average improvement of hourly forecast by 1 to 2 % can be achieve by including such weather factors.

Short-Term Forecasting of Electricity Supply and Demand by Using the Wavelet-PSO-NNs-SO Technique for Searching in Big Data of Iran’s Electricity Market

The databases of Iran’s electricity market have been storing large sizes of data. Retail buyers and retailers will operate in Iran’s electricity market in the foreseeable future when smart grids are implemented thoroughly across Iran. As a result, there will be very much larger data of the electricity market in the future than ever before. If certain methods are devised to perform quick search in such large sizes of stored data, it will be possible to improve the forecasting accuracy of important variables in Iran’s electricity market. In this paper, available methods were employed to develop a new technique of Wavelet-Neural Networks-Particle Swarm Optimization-Simulation-Optimization (WT-NNPSO-SO) with the purpose of searching in Big Data stored in the electricity market and improving the accuracy of short-term forecasting of electricity supply and demand. The electricity market data exploration approach was based on the simulation-optimization algorithms. It was combined with the Wavelet-Neural Networks-Particle Swarm Optimization (Wavelet-NNPSO) method to improve the forecasting accuracy with the assumption Length of Training Data (LOTD) increased. In comparison with previous techniques, the runtime of the proposed technique was improved in larger sizes of data due to the use of metaheuristic algorithms. The findings were dealt with in the Results section.

Performance Analysis of Short-Term Electricity Demand with Atmospheric Variables

The quality of short-term electricity demand forecasting is essential for the energy market players for operation and trading activities. Electricity demand is significantly affected by non-linear factors, such as climatic conditions, calendar components and seasonal behavior, which have been widely reported in the literature. This paper considers parsimonious forecasting models to explain the importance of atmospheric variables for hourly electricity demand forecasting. Many researchers include temperature as a major weather component. If temperature is included in a model, other weather components, such as relative humidity and wind speed, are considered as less effective. However, several papers mention that there is a significant impact of atmospheric variables on electricity demand. Therefore, the main purpose of this study is to investigate the impact of the following atmospheric variables: rainfall, relative humidity, wind speed, solar radiation, and cloud cover to improve the forecasting accuracy. We construct three different multiple linear models (Model A, Model B, and Model C) including the auto-regressive moving average with exogenous variables (ARMAX) with the mentioned exogenous weather variables to compare the performances for Hokkaido Prefecture, Japan. The Bayesian approach is applied to estimate the weight of each variable with Gibbs sampling to approximate the estimation of the coefficients. The overall mean absolute percentage error (MAPE) performances of Model A, Model B, and Model C are estimated as 2.43%, 1.98% and 1.72%, respectively. This means that the accuracy is improved by 13.4% by including rainfall, snowfall, solar radiation, wind speed, relative humidity, and cloud cover data. The results of the statistical test indicate that these atmospheric variables and the improvement in accuracy are statistically significant in most of the hours. More specifically, they are significant during highly fluctuating and peak hours.

Short-term electricity demand forecasting using autoregressive based time varying model incorporating representative data adjustment

This paper presents the development of an autoregressive based time varying (ARTV) model to forecast electricity demand in a short-term period. The ARTV model is developed based on an autoregressive model by allowing its coefficients to be updated at pre-set time intervals. The updated coefficients help to enhance the relationships between electricity demand and its own historical values, and accordingly improve the performance of the model. In addition, a representative data adjustment procedure including a similar-day-replacement technique and a data-shifting algorithm is proposed in this paper to cultivate the historical demand data. These techniques help cleanse the raw data by mitigating the abnormal data points when daylight saving and holiday occur. Consequently, the robustness of the model is significantly enhanced, and accordingly the overall forecasting accuracy of the model is considerably improved. A case study has been reported in this paper by acquiring the relevant data for the state of New South Wales, Australia. The results show that the proposed model outperforms conventional seasonal autoregressive and neural network models in short term electricity demand forecasting.

Relative Entropy-Based Density Selection in Particle Filtering for Load Demand Forecast

Particle filtering (PF) is an eminent simulation-based state estimation technique, which is capable of handling massive data sets and diverse external factors. Here, an effective selection of the importance density plays a pivotal role in performances of PFs by not only preventing degeneracy problems at early stages of process, but also taking both the transition prior and likelihood into account when the likelihood appears in the tail of the prior. To this end, we propose a novel importance density selection scheme for PF based on the minimum relative entropy principle. Theoretical derivation of the proposed scheme is presented, and its effectiveness is evaluated against various sampling schemes that exist in the literature using synthetic experiments. Finally, the performance of the proposed minimum relative entropy-based density selection scheme is successfully demonstrated for short-term electricity demand forecasting of a company located in Miami, FL, USA.

Short-term power load forecasting with ordinary differential equation substitutions of polynomial networks

The purpose of the short-term electricity demand forecasting is to forecast in advance the system load, represented by the sum of all consumers load at the same time. Power load forecasting is important for an economically efficient operation and effective control of power systems and enables to plan the load of generating units. A precise load forecasting is required to avoid high generation costs and the spinning reserve capacity. Under-prediction of the demands leads to an insufficient reserve capacity preparation and can threaten the system stability, on the other hand, over-prediction leads to an unnecessarily large reserve that leads to high cost preparations. Differential polynomial neural network is a new neural network type, which decomposes and solves the selective general partial differential equation, which can model a searched function on the bases of observed data samples. It produces an output sum combination of convergent series of selected relative polynomial derivative terms, which can substitute for an ordinary differential equation solution to describe and forecast real data time-series. Partial derivative terms of several time-point variables substitute for the time derivatives of the converted general ordinary differential equation. The operating principles of the proposed method differ significantly from other conventional neural network techniques.

Short-term forecasting of electricity demand for the residential sector using weather and social variables

The aim of this study is to provide a precise model for the one-month-ahead forecast of electricity demand in the residential sector. In this study, a total of 20 influential variables are considered including monthly electricity consumption, 14 weather variables, and five social variables. Based on support vector regression and fuzzy-rough feature selection with particle swarm optimization algorithms, the proposed method established a model with variables that relate to the forecast by ignoring variables that inevitably lead to forecasting errors. The proposed forecasting model was validated using historical data from South Korea between January 1991 and December 2012. The first 240 months were used for training and the remaining 24 for testing. The performance was evaluated using MAPE, MAE, RMSE, MBE, and UPA values. Furthermore, it was compared with that obtained from the artificial neural network, auto-regressive integrated moving average, multiple linear regression models, and the methods proposed in the previous studies. It was found to be superior for every performance measure considered in this study. The proposed method has an advantage over the previous methods because it automatically determines appropriate and necessary variables for a reliable forecast. It is expected that it can contribute to more accurate forecasting of short-term electricity demand in the residential sector. The ability to accurately forecast short-term electricity demand can assist power system operators and market participants in ensuring sustainable electricity planning decisions and securing electricity supply for the consumers.

Short-term Power Demand Forecasting using the Differential Polynomial Neural Network

AbstractPower demand forecasting is important for economically efficient operation and effective control of power systems and enables to plan the load of generating unit. The purpose of the short-term electricity demand forecasting is to forecast in advance the system load, represented by the sum of all consumers load at the same time. A precise load forecasting is required to avoid high generation cost and the spinning reserve capacity. Under-prediction of the demands leads to an insufficient reserve capacity preparation and can threaten the system stability, on the other hand, over-prediction leads to an unnecessarily large reserve that leads to a high cost preparations. Differential polynomial neural network is a new neural network type, which forms and resolves an unknown general partial differential equation of an approximation of a searched function, described by data observations. It generates convergent sum series of relative polynomial derivative terms which can substitute for the ordinary differ...

A self-similar local neuro-fuzzy model for short-term demand forecasting

This paper proposes a self-similar local neuro-fuzzy (SSLNF) model with mutual information-based input selection algorithm for the short-term electricity demand forecasting. The proposed selfsimilar model is composed of a number of local models, each being a local linear neuro-fuzzy (LLNF) model, and their associated validity functions and can be interpreted itself as an LLNF model. The proposed model is trained by a nested local liner model tree (NLOLIMOT) learning algorithm which partitions the input space into axis-orthogonal sub-domains and then fits an LLNF model and its associated validity function on each sub-domain. Furthermore, the proposed approach allows different input spaces for rule premises (validity functions) and consequents (local models). This appealing property is employed to assign the candidate input variables (i.e., previous load and temperature) which influence short-term electricity demand in linear and nonlinear ways to local models and validity functions, respectively. Numerical results from short-term load forecasting in the New England in 2002 demonstrated the accuracy of the SSLNF model for the STLF applications.