Enhancing Electricity Load Forecasting with Machine Learning and Deep Learning

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

Accurate electrical load forecasting is of great significance to help power companies in better scheduling and efficient management. Since high levels of uncertainties exist in the load time series, it is a challenging task to make accurate short-term load forecast (STLF). In recent years, deep learning approaches provide better performance to predict electrical load in real world cases. The convolutional neural network (CNN) can extract the local trend and capture the same pattern, and the long short-term memory (LSTM) is proposed to learn the relationship in time steps. In this paper, a new deep neural network framework that integrates the hidden feature of the CNN model and the LSTM model is proposed to improve the forecasting accuracy. The proposed model was tested in a real-world case, and detailed experiments were conducted to validate its practicality and stability. The forecasting performance of the proposed model was compared with the LSTM model and the CNN model. The Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were used as the evaluation indexes. The experimental results demonstrate that the proposed model can achieve better and stable performance in STLF.

Demand side management has a vital role in supporting the demand response in smart grid infrastructure, in the decision-making of energy management, in household applications is significantly affected by the load-forecasting accuracy. This paper introduces an innovative methodology to enhance household demand forecasting based on energy disaggregation for Short Term Load Forecasting. This approach is constructed from Feed-Forward Artificial Neural Network forecaster and a pre-processing stage of energy disaggregation. This disaggregation technique extracts the individual appliances’ load demand profile from the aggregated household load demand to increase the training data window for the proposed forecaster. These proposed algorithms include two benchmark disaggregation algorithms; Factorial Hidden Markov Model (FHMM), Combinatorial Optimization in addition to three adopted Deep Neural Network; long short- term memory (LSTM), Denoising Autoencoder, and a network which regress start time, end time, and average power. The proposed load forecasting approach outperformed the currently available state-of-the-art techniques; namely root mean square error (RMSE), normalized root mean square error (NRMSE), and mean absolute error (MAE).

Short-term electricity load forecasting provides a basis for day-ahead energy scheduling. To improve the accuracy of short-term electricity load forecasts and deeply explore the temporal characteristics of load sequences, a method is proposed to extract predictable components of load sequences based on the secretary bird optimization algorithm (SBOA)-optimized successive variational mode decomposition (SVMD). This method decomposes the electricity load sequence into multiple subsequences under different time series. The combined forecasting architecture of the temporal convolutional network (TCN) and the bidirectional long short-term memory network (BiLSTM) is introduced to mine the temporal characteristics of each load component, resulting in short-term load forecasting outcomes. A case study is conducted using the annual electricity load data for the year 2018 from a specific region in Belgium. The experimental results show that the mean absolute error (MAE) of the TCN–BiLSTM model is reduced by 47.8%, 32.8%, and 11.5%, respectively, compared to other models. The root mean square error (RMSE) is reduced by 42.9%, 39.2%, and 11.3%, respectively, and the average goodness of fit R2 is reduced by 9.81%.

Short-term residential load forecasting plays a crucial role in smart grids, ensuring an optimal match between energy demands and generation. With the inherent volatility of residential load patterns, deep learning has gained attention due to its ability to capture complex nonlinear relationships within hidden layers. However, most existing studies have relied on default loss functions such as mean squared error (MSE) or mean absolute error (MAE) for neural networks. These loss functions, while effective in overall prediction accuracy, lack specialized focus on accurately predicting load peaks. This article presents a comparative analysis of soft-DTW loss function, a smoothed formulation of Dynamic Time Wrapping (DTW), compared to other commonly used loss functions, in order to assess its effectiveness in improving peak prediction accuracy. To evaluate peak performance, we introduce a novel evaluation methodology using confusion matrix and propose new errors for peak position and peak load, tailored specifically for assessing peak performance in short-term load forecasting. Our results demonstrate the superiority of soft-DTW in capturing and predicting load peaks, surpassing other commonly used loss functions. Furthermore, the combination of soft-DTW with other loss functions, such as soft-DTW + MSE, soft-DTW + MAE, and soft-DTW + TDI (Time Distortion Index), also enhances peak prediction. However, the differences between these combined soft-DTW loss functions are not substantial. These findings highlight the significance of utilizing specialized loss functions, like soft-DTW, to improve peak prediction accuracy in short-term load forecasting.

Essentially, Electricity Load Forecasting is an approximation of upcoming active loads from a variety of load buses before the active loads occur. Also, it is an important factor for power system energy management. Accurate and precise load forecasting can help to reduce the capacity of the power system, to make unit commitment decisions, and to increase the dependability of power systems. Hence, this paper presents a generalized regression Neural Network (GRNN) based approach for Short Term Load Forecasting (STLF). The results showed that the performance of GRNN with 30 neurons is better of short-term load forecasting in comparison with 10 neurons. For 10 neurons, the Mean Absolute Percentage Error (MAPE) was 2.10% and Mean Absolute Error (MAE) was 306.21 MWh. However, for 30 neurons it was observed that MAPE is 1.81% and MAE 268.48 MWh.

Load forecasting based on grasshopper optimization and a multilayer feed-forward neural network using regressive approach

Electrical Load forecasting plays a significant part for power systems planning, operation and control for efficacy companies as well as policy makers to develop the reliable as well as stable energy infrastructure. Various approaches like conservative, Artificial Intelligence (AI) as well as hybrid approaches had been introduced to analyze the short-term load forecasting. However, these approaches had faced several problems like low convergence speed, high computational complexity and minimum prediction accuracy. To overcome these challenges, this research proposes the hybrid method of improved Support Vector Machine (SVM) and Grasshopper Optimization Algorithm (GOA) called SVM-GOA based feature section and hyperparameter optimization for electrical load forecasting. In pre-processing step, the min-max normalization technique is used for the scaling the feature data. Furthermore, the proposed SVM-GOA is trained and tested by simulations on the Singapore dataset. The effectiveness of the proposed SVM-GOA is estimated by various performance metrics like Root Mean Square Error (RMSE), Mean Absolute Percent Error (MAPE), Mean Absolute Error (MAE), R-Square (R2) and it achieves the values of 0.6547, 2.13, 0.69 respectively when compared to the previous methods like Artificial Neural Network (ANN) and Federated Learning (FL).

Accurate load forecasting is essential for reliable and efficient operation of power systems. Traditional forecasting methods often struggle with capturing complex nonlinear patterns in load data. Artificial neural networks (ANNs) have emerged as a promising alternative due to their ability to learn complex relationships from historical data (Syed et al. in IEEEA 9:54992–55008, 2021. https://doi.org/10.1109/ACCESS.2021.3071654). This study investigates the potential of ANNs for short-term peak load forecasting in a 150 kV power system in Semarang, Indonesia. The study examines the impact of different input variables, including historical peak load, minimum load, population, and energy production, on forecasting accuracy. Several ANN architectures are trained and evaluated using mean absolute percentage error (MAPE) and mean squared error (MSE) metrics as reported by Demuth and De Jesús (neural network design). The results indicate that ANNs can achieve high accuracy in predicting peak load, with MAPE values below 10%. The study also demonstrates the importance of carefully selecting input variables and training parameters for optimal model performance. The findings highlight the potential of ANNs for improving load forecasting accuracy in power systems, contributing to enhanced grid reliability and operational efficiency. The findings of this study contribute to a deeper understanding of the application of ANNs in power system load forecasting. They demonstrate the potential of ANNs to achieve high accuracy and provide valuable insights into the factors influencing model performance. The findings are relevant for power system operators, researchers, and policymakers working to improve grid reliability and efficiency as reported by Prabha Kundur and Malik (Power System Stability and Control, McGraw-Hill Education, New York, 2022. https://www.accessengineeringlibrary.com/content/book/9781260473544).

Minimization of electrical energy wastage and provision of its regular supply make electrical load forecasting an important aspect of the power infrastructure. An accurate load forecasting is crucial for the reduction of the cost of electrical energy generation and spinning reserve capacity. Therefore, in this study, fuzzy logic (FL) technique was employed for the projection of electrical energy demand on short-term basis. The FL model was trained using the six months hourly load and temperature data respectively obtained from 132/33 kV Ikeja West Transmission Station, Ayobo and Nigerian Meteorological Agency, Oshodi, Lagos State, Nigeria. Triangular and trapezoidal membership functions (MFs) were used in the training of the model with Mamdani fuzzy inference system. The time, load and temperature inputs were fuzzified into six, four and three MFs respectively while the fuzzification process used 25 fuzzy rule bases. The centroid method of defuzzification was used to change the results into readable values. The adequacy of the FL model was determined using five metrics including mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), chi square (χ2) and F- test. The obtained results revealed that the FL model developed excelled in all the five tests of adequacy considered with MSE, MAE, MAPE, χ2 and F-test values of 4.17, 6.74, 11.51%, 7.93 and 1.27 respectively and hence, performed satisfactorily. This work established that the fuzzy logic approach is appropriate for electrical load projection on short-term basis.

Under the dual pressures of global carbon emission reduction and production cost control, energy-intensive industrial enterprises are in urgent need of a balanced low-carbon operation strategy that reconciles economic benefits, environmental performance and production continuity. To address the limitations of existing methods in multi-dimensional objective balancing, this paper proposes a dynamic multi-objective optimization framework for industrial electricity consumption, integrating high-precision load forecasting and optimal scheduling. For load forecasting, an improved dual-gate optimization temporal attention long short-term memory (DGO-TA-LSTM) model is developed, which is modeled based on the one-year hourly electricity operation data (8760 samples) of a high-energy industrial enterprise in southern China, and its performance is verified via three standard metrics—the mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE)—compared with five mainstream baseline models. On this basis, when taking time-varying electricity-carbon factors and time-of-use electricity prices as dual guiding signals, a three-objective optimization model minimizing electricity cost, carbon emissions and load deviation is constructed, which is solved by the Non-Dominated Sorting Genetic Algorithm II (NSGA-II), with the Improved Gray Target Decision-Making (IGTD) method introduced to select the optimal compromise solution. Case study results show that the proposed scheme achieved a 1.9% reduction in electricity cost and a 30% reduction in carbon emissions compared with the unoptimized strategy, providing a feasible and scalable low-carbon operation path for industrial enterprises.

Accurate residential load forecasting is a key to achieve grid stability and efficient energy management. However, it becomes challenging due to the non-linear and seasonally fluctuating energy usage of domestic users. Existing statistical and machine learning-based forecasting models struggle to produce accurate forecasts due to dynamic and stochastic user behaviors for energy usage. On the other hand, pairwise ensemble methods can achieve higher forecasting accuracy in short-term load forecasting, but are not scalable and face generalization issues that often lead to overfitting and complexity in managing multivariate data. To address these limitations, we propose to integrate LightGBM, XGBoost and CatBoost models to systematically address the limitations of existing ensemble-based forecasting models. This integration aims to leverage the strengths of each ensemble method, where LightGBM handles generalization across multiple sites, XGBoost avoids overfitting the model, and CatBoost effectively manages categorical features. We implement our proposed model using a real-world, publicly available dataset for 13 residential locations in North America and Europe. The proposed model outperforms other state-of-the-art algorithms with the lowest root mean squared logarithmic error (RMSLE) values of 0.1898, while the coefficient of determination (R2) calculated from the data is 0.9745. Other evaluation measures such as root mean square error (RMSE), coefficient of variation of the root mean square error (CVRMSE) and mean bias error (MBE) also support the proposed approach regarding the efficiency of the model.Finally, we also perform an ablution study to show predictive efficacy of incremental model integration.

Accurate short-term prediction of residential power consumption is imperative for efficient energy system management. However, the complexity of high-resolution load data, nonlinear dynamics of load fluctuation, and external factor interactions pose challenges to traditional load forecasting methods. This work introduces a diffusion model-based and attention mechanism-enhanced temporal forecasting framework to address the volatility and uncertainty in load patterns. The proposed model enhances the noise robustness via diffusion processes, captures multi-scale temporal features through temporal convolutional networks, and adaptively focuses on critical time steps using attention mechanisms. Further, a dynamically weighted loss function is designed to improve both the prediction accuracy and latent representation quality. Experiments on multiple real-world residential load datasets show that the proposed model always outperforms benchmarks, reducing on average the mean absolute error (MAE) by 47.4%, symmetric mean absolute percentage error (SMAPE) by 39.7%, and mean absolute percentage error (MAPE) by 57.6%. It also achieves the superior root mean square error (RMSE) and Pearson correlation coefficient (PCC) performance, validating its effectiveness for high-resolution and multi-modal load forecasting.

The smart buildings’ load forecasting is necessary for efficient energy management, and it is easily possible because of the data availability based on widespread use of Internet of Things (IoT) devices and automation systems. The information of buildings’ occupancy is directly associated with energy consumption. Therefore, we present a hybrid model consisting of a Long Short-Term Memory (LSTM) network, Extreme Gradient Boosting (XgBoost), Random Forest (RF) and Linear Regression (LR) for commercial and academic buildings’ load forecasting. The correlation between occupants’ count and total load of the building is calculated using Pearson Correlation Coefficient (PCC). The comparative analysis of the proposed approach with LSTM, XgBoost, RF and Gated Recurrent Unit (GRU) is also performed. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE) and Normalized Root Mean Square Error (NRMSE) are used as performance indicators for evaluating performance. Findings indicate that the proposed hybrid approach outperforms other models. The RMSE and MAE of 2.99 and 2.18, respectively, are recorded by the proposed model for commercial building dataset while for academic building the RMSE and MAE are 4.48 and 2.85, respectively. Occupancy and load consumption have a positive correlation as evident from PCC analysis. Therefore, we have scheduled the forecasted load based on occupancy patterns for two different cases. Cost is reduced by 17.42% and 33.40% in case 1 and case 2, respectively. Moreover, the performance of the proposed hybrid approach is compared with different techniques presented in literature for buildings load forecasting.

Accurate short-term load forecasting (STLF) is critical to the operation and control of the power grid. In the literature, deep learning techniques have shown its superiority for accurate load forecasting over other methods due to its strong regression ability. However, the training process of the deep learning systems is time-consuming providing that they contain a large number of parameters due to the complex structure. This paper presents a novel broad learning system (BLS) approach for load forecasting. The BLS, which is established as a flat network, is an alternative to the deep learning system by expanding the structure in a wide sense. The expanded broad structure of BLS ensures its strong approximation capability of nonlinear mapping. Moreover, the BLS has a much faster training process compared to deep learning due to its simple structure. The proposed method is tested with an open dataset at low-voltage level from Australia and the testing results demonstrate the effectiveness of the proposed method.