Short-Term Load Forecasting Method for Low Voltage Users Based on Deep Belief Neural Network

Short-term load forecasting plays a vital role for the power system’s safe operation and production arrangements. This paper regards electric load forecasting as a nonlinear time series prediction problem, and establishes the electric load autoregressive prediction model (ARX Model) based on historical load data, approaching ARX model parameters with RBF neural network, estimating model parameters with using a Structured Nonlinear Parameters Optimization Method (SNPOM), proposing cycle prediction method for short-term electric load forecasting. Experimental results show that the method has higher prediction accuracy for short-term electric load forecasting. Keywords: Short-term load forecasting; time series; RBF-ARX model; cycle forecasting; structured nonlinear parameter optimization method

Short-term load forecasting is an important component of grid economic dispatching and the forecasting error directly affects the economy of grid operation. Different from wide area power grid, it is more difficult to implement short-term user load forecasting, especially existing missing data. The feature model about user load is constructed by analyzing the static, dynamic and distributed characteristics of user load. Then, based on gradient boosted decision trees and similar training samples, a short-term user load filling and forecasting model is proposed. Through predicting different types of user load in short-term, to analyze filling model about missing load data is helpful to improve the accuracy of short-term user load forecasting. And, the forecasting accuracy and its stability of the proposed model are validated.

Short-term load forecasting is viewed as one promising technology for demand prediction under the most critical inputs for the promising arrangement of power plant units. Thus, it is imperative to present new incentive methods to motivate such power system operations for electricity management. This paper proposes an approach for short-term electric load forecasting using long short-term memory networks and an improved sine cosine algorithm called MetaREC. First, using long short-term memory networks for a special kind of recurrent neural network, the dispatching commands have the characteristics of storing and transmitting both long-term and short-term memories. Next, four important parameters are determined using the sine cosine algorithm base on a logistic chaos operator and multilevel modulation factor to overcome the inaccuracy of long short-term memory networks prediction, in terms of the manual selection of parameter values. Moreover, the performance of the MetaREC method outperforms others with regard to convergence accuracy and convergence speed on a variety of test functions. Finally, our analysis is extended to the scenario of the MetaREC_long short-term memory with back propagation neural network, long short-term memory networks with default parameters, long short-term memory networks with the conventional sine-cosine algorithm, and long short-term memory networks with whale optimization for power load forecasting on a real electric load dataset. Simulation results demonstrate that the multiple forecasts with MetaREC_long short-term memory can effectively incentivize the high accuracy and stability for short-term power load forecasting.

In electrical engineering load forecasting have been tried out using traditional forecasting models and artificial intelligence techniques and have become one of the major research fields. An accurate and efficient Short-term load forecasting (STLF) plays a vital role for economic operational planning of both regulated power systems and electricity markets. To develop a solution/methodology to demand forecast (Hourly load forecast) and by incorporating weather conditions. However, STLF it is pertinent to understand conventional methods. Therefore, popular conventional methods were implemented to learn methods for STLF. This paper presents Simple Moving Average, Weighted Moving Average, Exponential Moving Average, Auto Regressive and Multiple linear regressions for short term load forecasting. Conventional technique approach is implemented on historical load data for forecasting the load. PGVCL hourly load data used for training and testing is collected from ALDC, Jetpur, Gujarat. Hence hereby in this paper I have compared five conventional methods for STLF and have come out with a result that forecasting errors of time series models gives reasonably accurate hour ahead load forecast.

Short-term electric load and temperature forecasting using wavelet echo state networks with neural reconstruction

Power system load is a stochastic and non-stationary process. Due to the influence of various factors, some bad data may exist in the load observation value. These data are mixed into the normal load data to participate in the training of neural network, which seriously affects the accuracy of load forecasting. Short-term load forecasting is the basis of power system operation and analysis, improving the precision of load forecasting is an important means to ensure the scientific decision-making of power system optimization. In order to improve the precision of short term load forecasting in power system, a short-term load forecasting model based on genetic algorithm is proposed to optimize BP neural network. Firstly, using genetic algorithm to optimize the initial weights and thresholds of BP neural network to improve the prediction accuracy of BP neural network; Through the comparison and analysis before and after the model optimization, the experimental results with smaller prediction error were obtained. The simulation results show that the short-term load forecasting model established by this method has faster convergence rate and higher prediction precision.

Load forecasting has always been the focus of energy management system research. Recently, with the development of machine learning and artificial intelligence technology, more and more models are applied to load forecasting. In this paper, we design a model based on the temporal convolutional network for short-term load forecasting, which can accurately capture the feature form historical load data. Combine the actual load data collected from a certain region of Shanghai, we compare our model with three traditional models, including ARIMA model, ANN model, and LSTM model. The experiment results show that the model proposed in this paper achieves the best performance and has superior accuracy in short-term load forecasting.

Short-Term Residential Load Forecasting (STRLF) is a core task in smart grid dispatching and energy management, and its accuracy directly affects the economy and stability of power systems. Current mainstream methods still have limitations in addressing issues such as complex temporal patterns, strong stochasticity of load data, and insufficient model interpretability. To this end, this paper proposes an explainable and efficient forecasting framework named KAN+Transformer, which integrates Kolmogorov–Arnold Networks (KAN) with Transformers. The framework achieves performance breakthroughs through three innovative designs: constructing a Reversible Mixture of KAN Experts (RMoK) layer, which optimizes expert weight allocation using a load-balancing loss to enhance feature extraction capability while preserving model interpretability; designing an attention-guided cascading mechanism to dynamically fuse the local temporal patterns extracted by KAN with the global dependencies captured by the Transformer; and introducing a multi-objective loss function to explicitly model the periodicity and trend characteristics of load data. Experiments on four power benchmark datasets show that KAN+Transformer significantly outperforms advanced models such as Autoformer and Informer; ablation studies confirm that the KAN module and the specialized loss function bring accuracy improvements of 7.2% and 4.8%, respectively; visualization analysis further verifies the model’s decision-making interpretability through weight-feature correlation, providing a new paradigm for high-precision and explainable load forecasting in smart grids. Collectively, the results demonstrate our model’s superior capability in representing complex residential load dynamics and capturing both transient and stable consumption behaviors. By enabling more accurate, interpretable, and computationally efficient short-term load forecasting, the proposed KAN+Transformer framework provides effective support for demand-side management, renewable energy integration, and intelligent grid operation. As such, it contributes to improving energy utilization efficiency and enhancing the sustainability and resilience of modern power systems.

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.

Electricity load forecast needs to ensure minimum load wastage and requires intelligent decision-making systems to accurately predict future load demand. Learning capability, robustness and ability to solve nonlinear problems make ANN widely acceptable. For accurate short-term load forecast (STLF), an ensemble soft computing approach, namely ANN-PSOHm, composed of an artificial neural network (ANN) and particle swarm optimization (PSO) with homeostasis based mutation is presented in this article. To enhance the learning strength of ANN, PSO undergoes homeostasis mutation to bring greater diversity among solutions by exploring in wider search space. To demonstrate the effectiveness of ANN, three case studies on load data of NEPOOL region (courtesy ISO New England) are performed. The experimental results show that ANN-PSOHm improves accuracy by 11.57% MAPE over ANN-PSO.

With the promotion of power market reform, accurate short-term load forecasting is of great significance for power systems to formulate reasonable production plans and ensure safe operation of the power grid. At present, the power grids have brought great challenges to load forecasting, and due to the need of production, a large number of nonlinear, asymmetric, and impact loads are connected to the power grid, so it is difficult for traditional power load forecasting methods to fully and accurately characterize the load characteristics. In order to learn the complex hidden deep relationship in nonlinear load data and improve the prediction accuracy, this paper proposed a method based on conditional generative adversarial networks (CGANs). This method used a convolutional neural network to construct a generative model and a discriminant model, took the load influencing factor as a condition. Through the game training of the confrontation network, the generation model can learn the mapping relationship between the noise and the real load data, to perform short-term load forecasting. The validation was conducted using a dataset from a certain power plant, and the experimental results showed that the trained CGAN has strong ability to learn load temporal features and has high prediction accuracy in different scenarios. The subsequent work will analyze the characteristics of different types of load data and consider the impact of real-time electricity prices and other factors on load prediction, so as to further improve the prediction accuracy and universality of the model.

The forecasting of the user’s short-term power load has always been a matter of concern for the power supply department. The traditional ensemble learning method for load prediction is generally random forest (RF), and XGBoost as a newly proposed ensemble learning method has improved algorithm generalization ability and prediction accuracy compared with RF. This paper considers the influence of climatic factors such as wind speed, humidity on short-term load, and establishes a short-term load forecasting model based on XGBoost in combination with historical load data. Experiments were conducted using users’ load data from an industrial park in China, and compared with the RF. The experiment shows the effectiveness and superiority of XGBoost algorithm in short-term load forecasting.

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%.

This research paper investigates the application of artificial neural networks (ANNs) and fuzzy logic methods for short-term load forecasting in the Western Libyan Electric Network. Historical hourly load data collected during the year 2023 by the General Electricity Company of Libya (GECOL). The study aims to develop accurate and reliable load forecasting models to support efficient grid operation and resource planning. Historical load data and meteorological variables are utilized to train and evaluate the forecasting models. The performance of the ANNs and fuzzy logic methods is compared, and the suitability of each approach for load forecasting in the Western Libyan Electric Network is assessed. The results demonstrate the effectiveness of both ANNs and fuzzy logic methods in short-term load forecasting, providing valuable insights for electricity providers and policymakers in the region. Keywords: neural' networks, fuzzy logic, load forecasting

Short-term load forecasting is essential for the power company's operation and grid operators because it is necessary to ensure adequate capacity and proper power generation arrangement; this will affect operating efficiency and short-term decisions. Meanwhile, the Covid-19 epidemic as a nonlinear factor will be effective in short-term load forecasting and based on previous solutions, electrical load forecasting may not be accurate. A nonlinear and complex relationship between the factors affecting the load forecasting problem explains the need to use intelligent methods such as machine learning. This paper analyses the effect of Covid-19 epidemic countermeasures on short-term electric load forecasting in Iran. To forecast the short term electrical load, a deep neural network with a hybrid architecture and peak power consumption data, average temperature, and Covid-19 epidemic countermeasure data over 15 months during the Covid-19 epidemic was used. The results indicate an increase in forecasting accuracy considering the countermeasure's data. Also, the proposed model validation with data related to the fourth wave of the Covid-19 epidemic and the data of countermeasures modeling in Iran show the effectiveness and reasonable accuracy of the proposed model during the Covid19 epidemic.