Long-term Load Forecasting Research Articles

Decomposition framework for long term load forecasting on temperature insensitive area

Long-term load forecasting (LTLF) with hourly resolution provides more information for power system planning and becomes increasingly important as the growing penetration of renewable energy sources intensifies system uncertainties. In most LTLF literature, temperature is used as the main driving factor. However, the system load in an area with a high proportion of industrial energy consumption or rich diversity of climate zones is less meteorologically sensitive, which makes it challenging to implement LTLF. To address this issue, we propose a decomposition framework with industrial and temperature-sensitive components separated from the electric load and modeled, respectively. For the industrial component, a seldom-used macroeconomic variable, industrial gross products, is fed into modeling. For the temperature-sensitive component, temperature and its variants are input for modeling via variable selection. With serial and parallel modeling schemes, we further propose two decomposition models under this framework, where one, denoted as DeSerial, models two components serially, while the other, denoted as DeParallel, models them in a parallel way. Compared with representative models, the proposed two decomposition models produce more accurate monthly and annual load forecasts for the selected region, whose system load is less sensitive to temperature but more to the industries.

Long-term load forecasting for smart grid

Abstract The load forecasting problem is a complicated non-linear problem connected with the weather, economy, and other complex factors. For electrical power systems, long-term load forecasting provides valuable information for scheduling maintenance, evaluating adequacy, and managing limited energy supplies. A future generating, transmission, and distribution facility's development and planning process begins with long-term demand forecasting. The development of advanced metering infrastructure (AMI) has greatly expanded the amount of real-time data collection on large-scale electricity consumption. The load forecasting techniques have changed significantly as a result of the real-time utilization of this vast amount of smart meter data. This study suggests numerous approaches for long-term load forecasting using smart-metered data from an actual distribution system on the NIT Patna campus. Data pre-processing is the process of converting unprocessed data into a suitable format by eliminating possible errors caused by lost or interrupted communications, the presence of noise or outliers, duplicate or incorrect data, etc. The load forecasting model is trained using historical load data and significant climatic variables discovered through correlation analysis. With a minimum MAPE and RMSE for every testing scenario, the proposed artificial neural network model yields the greatest forecasting performance for the used system data. The efficacy of the proposed technique has been through a comparison of the acquired results with various alternative load forecasting methods.

Optimizing Models and Data Denoising Algorithms for Power Load Forecasting

To handle the data imbalance and inaccurate prediction in power load forecasting, an integrated data denoising power load forecasting method is designed. This method divides data into administrative regions, industries, and load characteristics using a four-step method, extracts periodic features using Fourier transform, and uses Kmeans++ for clustering processing. On this basis, a Transformer model based on an adversarial adaptive mechanism is designed, which aligns the data distribution of the source domain and target domain through a domain discriminator and feature extractor, thereby reducing the impact of domain offset on prediction accuracy. The mean square error of the Fourier transform clustering method used in this study was 0.154, which was lower than other methods and had a better data denoising effect. In load forecasting, the mean square errors of the model in predicting long-term load, short-term load, and real-time load were 0.026, 0.107, and 0.107, respectively, all lower than the values of other comparative models. Therefore, the load forecasting model designed for research has accuracy and stability, and it can provide a foundation for the precise control of urban power systems. The contributions of this study include improving the accuracy and stability of the load forecasting model, which provides the basis for the precise control of urban power systems. The model tracks periodicity, short-term load stochasticity, and high-frequency fluctuations in long-term loads well, and possesses high accuracy in short-term, long-term, and real-time load forecasting.

Model selection for long-term load forecasting under uncertainty

PurposeThe purpose of this study is to propose a systematic model selection procedure for long-term load forecasting (LTLF) for ex-ante and ex-post cases considering uncertainty in exogenous predictors.Design/methodology/approachThe different variants of regression models, namely, Polynomial Regression (PR), Generalised Additive Model (GAM), Quantile Polynomial Regression (QPR) and Quantile Spline Regression (QSR), incorporating uncertainty in exogenous predictors like population, Real Gross State Product (RGSP) and Real Per Capita Income (RPCI), temperature and indicators of breakpoints and calendar effects, are considered for LTLF. Initially, the Backward Feature Elimination procedure is used to identify the optimal set of predictors for LTLF. Then, the consistency in model accuracies is evaluated using point and probabilistic forecast error metrics for ex-ante and ex-post cases.FindingsFrom this study, it is found PR model outperformed in ex-ante condition, while QPR model outperformed in ex-post condition. Further, QPR model performed consistently across validation and testing periods. Overall, QPR model excelled in capturing uncertainty in exogenous predictors, thereby reducing over-forecast error and risk of overinvestment.Research limitations/implicationsThese findings can help utilities to align model selection strategies with their risk tolerance.Originality/valueTo propose the systematic model selection procedure in this study, the consistent performance of PR, GAM, QPR and QSR models are evaluated using point forecast accuracy metrics Mean Absolute Percentage Error, Root Mean Squared Error and probabilistic forecast accuracy metric Pinball Score for ex-ante and ex-post cases considering uncertainty in the considered exogenous predictors such as RGSP, RPCI, population and temperature.

The COVID-19 pandemic's impact on user consumption: A shift towards very efficient load forecasting

The COVID-19 pandemic has prompted significant shifts in energy consumption patterns, necessitating a departure from traditional data analysis methods. Accurate energy forecasting models play a crucial role in various domains of planning and energy management. It is possible to predict the demand for electricity consumption using a variety of techniques. Fundamentally, this research comprises two main components. The first phase assesses the influence of the COVID-19 pandemic on user consumption patterns through time series analysis. The subsequent segment is dedicated to long-term load forecasting, employing both statistical methods termed as Holt-Winters and Prophet algorithms and an Artificial Neural Network approach known as Long Short-Term Memory. These approaches aim to predict electricity demand amid the diverse and intricate context of the COVID-19 pandemic. It utilizes both conventional time series forecasting methods and advanced Artificial Intelligence models to enhance the accuracy of load forecasting. Since rapid societal and economic shifts are unpredictable during a pandemic, methods based on Artificial Intelligence are becoming extremely important due to its high precision. Though, it is problematic to conduct load prediction with high accuracy because of influencing factors like climatic, socioeconomic, and seasonal aspects. Finally, using hourly-driven power consumption data from Houston, Texas, USA, the Long Short-Term Memory model outperforms the Holt-Winters and Prophet models in a test of generalizability and accuracy. It is possible to verify the accuracy of experimental findings by analyzing the resulting constraints and influential factors.

An online long-term load forecasting method: Hierarchical highway network based on crisscross feature collaboration

In order to ensure the efficient operation of the power system, accurate online load forecasting is necessary. Existing studies face challenges in addressing unconventional load changes in long-term load forecasting (LTLF) and are unsuitable for online forecasting due to their reliance on measured Forecast Day Data (FDD). The development of a model independent of prior knowledge is essential to improve the interpretability and applicability of load forecasting methods. In this study, a hybrid model based on Crisscross Feature Collaboration (CFC) and Hierarchical Highway Network (HHN) is introduced. During the horizontal feature learning, the HHN is employed to learn temporal information from annual load curves across multiple time scales, reducing time complexity in LTLF. Subsequently, the prediction results of various time scales are combined to approximate FDD, addressing data leakage problems. In the vertical feature matching phase, the similar day data are screened by the multi-modal information of FDD and the Toeplitz Inverse Covariance Based Clustering (TICC) method, enabling the model to be independent of prior knowledge. Finally, through the HHN, all similar day data are utilized to reconstruct the forecasting load curve. In LTLF, the Root Mean Square Error (RMSE) of the proposed model reduces by 94.35 %, 85.74 %, 84.02 %, 90.72 %, 85.17 % and 87.76 % respectively in different scenarios compared to the direct forecasting. This signifies the effectiveness of our model in predicting the unconventional load change and achieving accurate online LTLF.

Modelling and Distribution of Electricity Load Forecasting in Nigeria Power System (Olu-Ode Community)

To plan for energy generation to fulfill customer demand as the population grows, load forecasting is often used to anticipate and predict a region's power demand growth. A power load To sell, plan, and purchase energy for power systems, forecasting might be employed. From electrical energy production through distribution, it is highly helpful. Power system forecasting may be broadly categorized into three classes: An hour to a week is considered short-term electric load forecasting, a week (7 days) to a year is considered medium-term electric load forecasting, and a year and beyond is considered long-term electric load forecasting. In emerging nations where the energy demand is erratic due to fast economic expansion and a rise in the rate of rural-urban migration, accurate load forecasting may aid in creating a strategy. Various load forecasting techniques, including expert systems, fuzzy logic, regression techniques, and artificial neural networks (ANN), were researched. However, current methods may only sometimes provide more accuracy in predicting short-term stress. To address this issue, a novel strategy for anticipating short-term load is put forward in this study. Long short-term memory (LSTM) and convolutional neural networks are included in the created approach. The technique is used to anticipate the short-term electrical demand for the power system in Nigeria. Additionally, the usefulness of the proposed method is confirmed by comparing the forecasting errors of the suggested method with those of other existing methods like the long short-term memory network, the radial basis function network, and the extreme gradient boosting algorithm. It is discovered that the suggested technique produces better short-term load forecasting precision and accuracy.

Modeling of Long‐Term Load Forecast in Jordan Based on Statistical Techniques

The paper proposes a mathematical model for long‐term load forecast (LTLF) based on parametric and time series statistical techniques. The flowchart of the proposed algorithm was also presented. The multiple linear regression (MLR) as well as the autoregressive integrated moving average (ARIMA) model with different model orders are employed in load forecasting. Historical data from 1990 to 2022 were utilized in the model implementation and validation. The input data imply gross domestic product (GDP), oil prices, population, and the energy from renewable energy projects as independent variables, and the annual peak load is the dependent variable. The results obtained by MLR show that population and GDP have a positive impact on electricity demand, whereas the oil price and the penetration of the renewable energy have a negative impact on electricity demand. In ARIMA, the load forecast is estimated based on error (residual) estimation that is determined based on the time lag operator and autoregressive and moving average coefficients. The ARIMA (p, d, and q) model with six different model orders is investigated. The Bayesian information criteria (BIC) and Akaike information criteria (AIC) indices are used as a measure in the selection of the appropriate model for prediction. The comparison between the six model’s scenarios shows that ARIMA (1, 1, 1) is the best model that fits the time series with minimum error and with the lowest BIC and AIC. The RMSE, MAPE, MSE, and MAE provided by ARIMA (1, 1, 1) are 3.57%, 2.55%, 0.13%, and 54.36, respectively, whereas the AIC and BIC are 386.8 and 394.0, respectively. A comparison between ARIMA and MLR shows that ARIMA is better than MLR in terms of time series fitting and error level. The LTLF forecast period covering the period 2024–2035 considers three scenarios of future development in the country: the normal (medium forecast), the optimistic (high forecast), and the pessimistic (low forecast). The forecast is made in the three directions (i.e., medium, high, and low) to avoid the ambiguity and uncertainty that may occur in the data input used in forecasting the electricity demand. A comparison between the MLR and ARIMA in the last year 2035 shows a small deviation between the two methods with the forecasted values in the range between 5480 MW and 5520 MW, respectively.

Daily load curve prediction for Jordan based on statistical techniques

AbstractThe article proposes a mathematical prediction model for daily load curves (DLCs) in Jordan from 2023–2050. The historical hourly peak loads based on the growth rate statistical method in 1994–2020 and the annual forecasted peak loads during the morning and evening periods taken from the long-term load forecast (LTLF) study of National Electric Power Company (NEPCO) during 2022–2050 are employed in the prediction model. The results show that the actual hourly growth rates, the annual forecasted growth rates, and the hourly peak loads in the reference year 2022 are the main input variables used in the prediction formula. The LTLF study conducted by NEPCO employs various sophisticated methods depending on the end-user sectorial electricity consumption that imply an econometric approach, market survey, and Gomprtz extrapolation techniques. The peak load in Jordan relies upon several climatic and nonclimatic variables, implying the ambient temperature, gross domestic product, income, demographic, urbanization, electricity tariff, average oil prices, and other factors related to technology and new aspects of energy saving and space heating/cooling systems, the DLC in Jordan is variable and changing from year to year. The proposed model considers a variation in the future DLC and suggests three different scenarios of DLC’s prediction based on the time occurrence of the peak load: the first is the daytime peak occurrence scenario, the second is the evening peak occurrence scenario, and finally is the daytime and evening peaks may be close to each other.

A Method for Medium and Long Term Electricity Consumption Forecasting in Regional Distribution Networks

Medium-term and long-term load forecasting is the basic data for formulating medium-term and long-term system maintenance plans and generation schedulings in the power system, and its prediction accuracy is crucial for the rationality of plan formulation. With the development of new energy generation units, a lot of distributed generation devices on the user side are connected to the distribution network, which harms the accuracy of load forecasting on distribution side. Therefore, a more accurate medium-term and long-term power forecasting method for the distribution network is needed. It is a primary problem for state grid to lack the historical electricity date. In response to this, some monthly electricity data are expanded by rolling daily electricity data. The diversity and multi-scale characteristics of factors affecting medium-term and long-term electricity demand limit the predictive performance of a single method. In response to this, a set empirical mode decomposition based on medium and long-term load electricity demand combination prediction method is proposed. Based on the fluctuation characteristics and patterns of each component after data decomposition, suitable prediction algorithms are used to predict each component separately, and finally, the predicted values of electricity demand are synthesized. The calculation results show that the prediction accuracy is effectively improved by the method of this paper.

Support vector regression based on improved Harris Hawk optimization algorithm for power load forecasting

Electricity load forecasting is an important part of power system operation, planning and management. Support vector regression (SVR) is a commonly used and efficient method for medium and long-term load forecasting. The hyperparameters of SVR have a very high influence on its performance and are not easily determined. In this paper, an improved Harris Hawk optimization algorithm (TAHHO) is proposed for optimizing the hyperparameters of SVR, and a TAHHO-SVR medium- and long-term prediction model is developed. TAHHHO enhances the convergence and stability of the original algorithm by introducing the survival of the fittest principle and the crossover operator of the artificial tree (AT) algorithm, which is validated in 13 benchmark test functions. The proposed TAHHO-SVR model is used for forecasting the UK National Grid dataset and demonstrates the feasibility and competitiveness of the model, which effectively improves the forecasting accuracy compared to HHO-SVR.

A Hybrid Feature Pyramid CNN-LSTM Model with Seasonal Inflection Month Correction for Medium- and Long-Term Power Load Forecasting

Accurate medium- and long-term power load forecasting is of great significance for the scientific planning and safe operation of power systems. Monthly power load has multiscale time series correlation and seasonality. The existing models face the problems of insufficient feature extraction and a large volume of prediction models constructed according to seasons. Therefore, a hybrid feature pyramid CNN-LSTM model with seasonal inflection month correction for medium- and long-term power load forecasting is proposed. The model is constructed based on linear and nonlinear combination forecasting. With the aim to address the insufficient extraction of multiscale temporal correlation in load, a time series feature pyramid structure based on causal dilated convolution is proposed, and the accuracy of the model is improved by feature extraction and fusion of different scales. For the problem that the model volume of seasonal prediction is too large, a seasonal inflection monthly load correction strategy is proposed to construct a unified model to predict and correct the monthly load of the seasonal change inflection point, so as to improve the model’s ability to deal with seasonality. The model proposed in this paper is verified on the actual power data in Shaoxing City.

Load Forecasting Research of Markov Chain based on Data Modeling

The introduction of the electricity market plays an irreplaceable role in assisting the power industry to achieve stable operation and planning of the power grid, promoting the effective use and dispatch of electric energy, and avoiding the waste of resources. The role of load forecasting for the electricity market is self-evident, in the context of big data, by building a load forecasting model based on the Markov chain, and using the actual data of a certain region for simulation calculation. The results show that the Markov forecasting method can play a good role in medium and long-term power load forecasting, and can be used as a supplement to conventional load forecasting.

Time-Varying approaches for Long-Term Electric Load Forecasting under economic shocks

Long-term Load Forecasting (LTLF) plays a vital role in the planning of electric utilities. In the long run, utilities face various uncertainties caused by economic and environmental factors. These uncertainties have made LTLF more complex and inaccurate, thus, amplifying financial risks of utilities. A potent contributor to such losses in LTLF accuracy is economic shocks. This study proposes two probabilistic Time-Varying (TV) approaches to capture such shocks in LTLF and minimise accuracy loss, namely TV-XGB-X and TV-PR, and their combinations considering economic policy uncertainty. Both eXtreme Gradient Boosting (XGB) and Polynomial Regression (PR) are extended to include the long-run TV effects of economic shocks as eXogeneous predictors in this paper. These models and their combinations are compared with various non-TV approaches through experiments on the monthly electricity consumption of eight energy-intensive states in the United States. The results reveal that the proposed combined approaches outperform stand-alone models on all datasets. The findings of this study can help utilities in hedging financial risks under shocks.

Diffusion Convolutional Recurrent Neural Network-Based Load Forecasting During COVID-19 Pandemic Situation

Infected by the novel coronavirus (COVID-19 – C-19) pandemic, worldwide energy generation and utilization have altered immensely. It remains unfamiliar in any case that traditional short-term load forecasting methodologies centered upon single-task, single-area, and standard signals could precisely catch the load pattern during the C-19 and must be cautiously analyzed. An effectual administration and finer planning by the power concerns remain of higher importance for precise electrical load forecasting. There presents a higher degree of unpredictability’s in the load time series (TS) that remains arduous in doing the precise short-term load forecast (SLF), medium-term load forecast (MLF), and long-term load forecast (LLF). For excerpting the local trends and capturing similar patterns of short and medium forecasting TS, we proffer Diffusion Convolutional Recurrent Neural Network (DCRNN), which attains finer execution and normalization by employing knowledge transition betwixt disparate forecasting jobs. This as well evens the portrayals if many layers remain stacked. The paradigms have been tested centered upon the actual life by performing comprehensive experimentations for authenticating their steadiness and applicability. The execution has been computed concerning squared error, Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). Consequently, the proffered DCRNN attains 0.0534 of MSE in the Chicago area, 0.1691 of MAPE in the Seattle area, and 0.0634 of MAE in the Seattle area.

Hybrid LSTM–BPNN-to-BPNN Model Considering Multi-Source Information for Forecasting Medium- and Long-Term Electricity Peak Load

Accurate medium- and long-term electricity peak load forecasting is critical for power system operation, planning, and electricity trading. However, peak load forecasting is challenging because of the complex and nonlinear relationship between peak load and related factors. Here, we propose a hybrid LSTM–BPNN-to-BPNN model combining a long short-term memory network (LSTM) and back propagation neural network (BPNN) to separately extract the features of the historical data and future information. Their outputs are then concatenated to a vector and inputted into the next BPNN model to obtain the final prediction. We further analyze the peak load characteristics for reducing prediction error. To overcome the problem of insufficient annual data for training the model, all the input variables distributed over various time scales are converted into a monthly time scale. The proposed model is then trained to predict the monthly peak load after one year and the maximum value of the monthly peak load is selected as the predicted annual peak load. The comparison results indicate that the proposed method achieves a predictive accuracy superior to that of benchmark models based on a real-world dataset.

Data Forecasting of Air-Conditioning Load in Large Shopping Malls Based on Multiple Nonlinear Regression

Abstract This article applies multiple nonlinear regression methods to establish a forecasting model for the load characteristics of air conditioning in shopping malls at different times. Based on Python data, determine the functional relationship of refrigerant parameters concerning pressure and temperature. The article uses kernel smoothing estimation technology to calculate the room temperature probability density distribution of users participating in DLC to characterize the user’s comfort. The article’s research results show that the average error between the regression analysis results of refrigerant parameters and the reference value is within 1%. This model is suitable for medium and long-term load forecasting. It has high prediction accuracy for the sudden change trend with a turning point.

Intelligence based Accurate Medium and Long Term Load Forecasting System

ABSTRACT In this study, we aim to provide an efficient load prediction system projected for different local feeders to predict the Medium- and Long-term Load Forecasting. This model improves future requirements for expansions, equipment retailing or staff recruiting to the electric utility company. We aimed to improve ahead forecasting by using hybrid approach and optimizing the parameters of our models. We used Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Multilayer perceptron (MLP) and hybrid methods. We used Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE) and squared error for comparison. To predict the 3 months ahead load forecasting, the lowermost prediction error was acquired using LSTM MAPE (2.70). For 6 months ahead forecasting prediction, MLP gives highest predictions with MAPE (2.36). Moreover, to predict the 9 months ahead load forecasting, the highest prediction has been attained using LSTM in terms of MAPE (2.37). Likewise, ahead 1 years MAPE (2.25) was yielded using LSTM and ahead six years MAPE (2.49) was provided using MLP. The proposed methods attain stable and better performance for prediction of load forecasting. The finding indicates that this model can be better instigated for future expansion requirements.

Mid- to Long-Term Electric Load Forecasting Based on the EMD–Isomap–Adaboost Model

Accurate load forecasting is an important issue for the reliable and efficient operation of a power system. In this study, a hybrid algorithm (EMDIA) that combines empirical mode decomposition (EMD), isometric mapping (Isomap), and Adaboost to construct a prediction mode for mid- to long-term load forecasting is developed. Based on full consideration of the meteorological and economic factors affecting the power load trend, the EMD method is used to decompose the load and its influencing factors into multiple intrinsic mode functions (IMF) and residuals. Through correlation analysis, the power load is divided into fluctuation term and trend term. Then, the key influencing factors of feature sequences are extracted by Isomap to eliminate the correlations and redundancy of the original multidimensional sequences and reduce the dimension of model input. Eventually, the Adaboost prediction method is adopted to realize the prediction of the electrical load. In comparison with the RF, LSTM, GRU, BP, and single Adaboost method, the prediction obtained by this proposed model has higher accuracy in the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and determination coefficient (R2). Compared with the single Adaboost algorithm, the EMDIA reduces MAE by 11.58, MAPE by 0.13%, and RMSE by 49.93 and increases R2 by 0.04.

Optimal placement of remote-controlled switches in distribution networks considering load forecasting

The application of long-term load forecasting (LTLF) in solving the problem of optimal placement of remote-controlled switches (RCSs) in distribution networks is considered in this paper. The mixed-integer linear programming (MILP) formulation for the RCSs placement problem is modified to include LTLF results obtained using the proposed reference historical load data model. Different methods are selected and validated in terms of forecasting accuracy. The modified MILP model for RCSs placement problem has been tested on distribution network RBTS-bus4 which has been used extensively for optimal switch placement studies. It is shown that LTLF results could significantly improve the accuracy of total cost estimation when compared to approximated constant annual load increase rates regularly used in previous research papers. Load profiling data have been included in LTLF analysis. The forecasting of annual U.S. dollar values has been performed to additionally improve the optimal solution accuracy. It is highly recommended for distribution companies to consider LTLF before making the final decision on RCSs investment.