Term Load Forecasting Research Articles

طرق التعلم الآلي للتنبؤ بالأحمال متوسطة المدى: دراسة على محطات شمال بنغازي التابعة للشركة العامة للكهرباء في شرق ليبيا

The General Electricity Company of Libya (GECOL) has experienced a surge in electricity demand in recent years, leading to power shortages, particularly during peak summer months. These shortages, often exacerbated by system outages caused by large generating unit failures or transmission line disruptions, have significantly impacted the country's stability. This is further compounded by the ongoing political instability in Libya, which, coupled with electricity supply issues, has negatively affected oil and gas production in some of the country's largest fields. This research addresses the challenge of electricity load demand forecasting by employing Machine Learning (ML) techniques, specifically focusing on Medium Term Load Forecasting (MTLF) based artificial intelligence algorithms. The study compares the accuracy and convergence of different ML methods against actual consumption data, aiming to identify the most effective approach. Accurate load forecasting is crucial for electrical utilities like GECOL to effectively meet customer demands and optimize power generation and transmission. Focusing on Benghazi, this research pioneers the application of Machine learning techniques to predict total energy consumption and demand. The study's findings are validated against real-world data obtained from GECOL's Benghazi Regional Control Center (BRCC), demonstrating the potential of ML for improving electricity load forecasting in Libya. The study concluded with the following results: The Extra Trees Regressor algorithm produced the best results for pregnancy as a target, with an accuracy value of 85%. The Huber Regressor algorithm produced the best results for deficit quantity as a target, with an accuracy value of 77%. Keywords: GECOL, Machine Learning, Load Forecasting, Medium Term Load Forecasting, MTLF.

Short-Term Power Load Forecasting Method Based on GRU-Transformer Combined Neural Network Model

Load Forecast (LF) is an important task in the planning, control and application of public power systems. Accurate Short Term Load Forecast (STLF) is the premise of safe and economical operation of a power system. In the research of short-term power load forecasting, machine learning and deep learning are the most popular methods at present, but there still exists a problem that the single and simple structure of power load forecasting model leads to low accuracy of load forecasting. In order to improve the accuracy of STLF, a Gated Cycle Unit (GRU)-Transformer combined neural network model is proposed. Transformer encoder structure is used as feature extractor to mine the complex mapping relationships between the input features and load. The advantage of self-attention mechanism is used to solve the problem of information loss of long sequences in short-term power load forecasting. At the same time, the multivariate time series model of GRU is used for model training. The experimental results on the power load data set of a certain region in southwest China and Panama City show that the proposed combined model prediction method has higher accuracy than those proposed in other literatures, which further proves its feasibility and superiority.

An optimized quad-ensemble short term load forecasting (STLF) method for electricity usage prediction using deep learning

An optimized quad-ensemble short term load forecasting (STLF) method for electricity usage prediction using deep learning

Metaheuristic approach to the Holt-Winters optimal short term load forecast

Electricity short-term load forecast is very important for the operation of power systems. In this work a classical exponential smoothing model, the Holt-Winters with double seasonality was used to test for accurate predictions applied to the Portuguese demand time series. Some metaheuristic algorithms for the optimal selection of the smoothing parameters of the Holt-Winters forecast function were used and the results after testing in the time series showed little differences among methods, so the use of the simple local search algorithms is recommended as they are easier to implement.

Highly fluctuating short-term load forecasting based on improved secondary decomposition and optimized VMD

Short Term Load Forecasting (STLF) is a critical task in the power sector, enabling efficient resource allocation and grid management. However, the volatile and complex nature of short-term load series pose significant challenges to forecasting models. Traditional decomposition-prediction models are bottlenecked in that they often lack complexity-based clustering for efficiency and optimization of decomposition for optimal secondary decomposition. In this paper, we summarize the framework of the decomposition-prediction models, and propose the hybrid model to address these limitations. We propose a Sample Entropy-based hierarchical clustering method to cluster components according to complexity and improve the efficiency of secondary decomposition. Additionally, we propose the center frequency method to efficiently optimize the K parameter of VMD, ultimately achieving the optimal decomposition. In summary, firstly, to help minimize the difficulty of prediction, the load series is decomposed twice using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Optimized Variational Mode Decomposition (OVMD). Then, two separate Long Short-Term Memory (LSTM) frameworks are built to predict the components obtained from the two decompositions, thus leveraging the advantages of the previous basic framework. Finally, by superimposing the prediction results, we obtain the output of the proposed model. The Belgian power load dataset is divided into four groups by season for comparison experiments. The results reveal that our model outperforms the benchmark models, with the best average coefficient of determination and mean absolute error of 0.996 and 53.69. Additionally, the limitations of sample entropy in secondary decomposition were revealed through our findings. These insights emphasize the promising contribution that our study brings in enhancing the decomposition-prediction model.

Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand

Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand

Research on short term load forecasting of power system based on gradient lifting tree

Research on short term load forecasting of power system based on gradient lifting tree

Transformer Implementation for Short Term Electricity Load Forecasting, Case Study: Bali, Indonesia

Short term load forecasting is a crucial process in ensuring optimal and reliable operation of electric power system which is critical in sustaining highly technological economies. Various approaches and methods have been implemented in forecasting electricity load of a system including statistical methods such as auto regression and machine learning methods such as support vector machine and also deep learning methodology as recurrent neural network methodology which gain popularity in electricity load forecasting nowadays. In this paper, Transformer as a deep learning methodology is used to forecast hourly electricity load in Bali Area. Three lookback days scenario and ten days of forecast period are used to evaluate the performance of the Transformer models. This study suggest that although higher lookback days will give more complicated model due to increasing number of parameters involved, the best overall prediction performance are given by transformer model with 1 day of lookback period. The three model in this study also tend to have low prediction performance in predicting electricity load for weekend or holiday period. Future study using multivariate transformer model is suggested to improve the prediction performance of the transformer model in predicting electricity load in Bali area.

Performance analysis and comparison of various techniques for short-term load forecasting

Rapidly varying load demand is one of the greatest problems that distribution system operators are now experiencing. Many researchers have been implemented the load demand requirement using traditional methods and machine learning methods. Both the methods have their own pros and cons according to dataset available for a particular site. This paper aims to predict load demand using different stochastic and deterministic approaches for short term load forecasting (STLF). Utilizing a variety of dependent characteristics, historical load data for two years is collected from IEEE dataport. The methods used in this study are exponential smoothing of traditional method and machine learning methods such as support vector machine (SVM), ensemble, artificial neural network (ANN), convolution neural network (CNN), long-short term memory (LSTM) and CNN-LSTM hybrid Model. All of these methods are compared and the best option is chosen of coefficient of correlation (R). The best method is found to be CNN-LSTM hybrid with R of 95.05%. The algorithm is implemented in PYTHON platform which is more compatible for machine learning applications.

Intelligent wild geese algorithm with deep learning driven short term load forecasting for sustainable energy management in microgrids

Energy management in power grids becomes essential to reduce the cost for the consumer and improve the power supply reliability. The microgrid is a vital part of the smart grid and it requires intelligent power management approach for effective functioning. Presently, delivering demand load and sustaining energy are two major challenges that exist in the power system. To resolve these problems, short-term load forecasting (STLF) models have been presented as an effective management and energy supply mode in power systems. The recently developed deep learning (DL) and machine learning (ML) models can be employed for accurate STLF in microgrids. In this view, this study presents an intelligent wild geese algorithm with deep learning driven short term load forecasting (IWGADL-STLF) model for sustainable energy management in microgrids. The proposed IWGADL-STLF model intends to accurately and rapidly predict the STLF in the microgrids. To accomplish this, the IWGADL-STLF model uses attention based Bi-directional long short term memory (ABiLSTM) model which involves the input parameters as formation of household and commercial load profiles with commercial load profile of the microgrid as output. The proposed IWGADL-STLF model identifies the behavioural patterns of parameters and models the behaviour in short time period for effective prediction process. Since hyperparameters play a vital role in the DL models, in this study, WGA is applied as a hyperparameter optimizer of the ABiLSTM model. The IWGADL-STLF approach has shown effective results with low MAE, MAPE, and R2 values. A comprehensive experimental analysis reported the enhanced performance of the presented model over the other existing approaches under several aspects.

A multi-information fusion model for short term load forecasting of an architectural complex considering spatio-temporal characteristics

Building load forecasting is critical for energy saving and carbon emission reduction, as building loads account for a rising percentage of energy consumption. Existing load forecasting methods only target a single building and do not consider the spatial characteristics of different building loads in an architectural complex, making it impossible to effectively forecast loads for all buildings in an architectural complex simultaneously. In this paper, considering the spatial correlation among building loads in an architectural complex, a novel short-term load forecasting method is proposed to improve the load forecasting accuracy for the architectural complex. First, Pearson correlation analysis is carried out to determine the key influencing factors of load, which are treated as multi-information. Then, to realize the load forecasting of all buildings in an architectural complex at the same time, a multi-information fusion model combined with a graph convolutional network and a long-short term memory network is proposed, and spatio-temporal attention modules are included to extract the dynamic spatio-temporal correlations of load. The performance of the proposed model is evaluated using actual load data from a public university in Beijing. When compared to other current methods, the experimental results show that the proposed model not only achieves the best results for architectural complex load forecasting (the largest MAPE is only 6.86%, the smallest R2 and Accuracy reach 0.87 and 0.85, respectively), but also maintains forecasting stability to some extent over a longer forecast period. The proposed method is a meaningful step towards achieving fast and accurate architectural complex load forecasting.

Short Term Load Forecasting of Residential and Commercial Consumers of Karnataka Electricity Board using CFNN

Electricity use and its access are correlated in the economic development of any country. Economically, electricity cannot be stored, and for stability of an electrical network a balance between generation and consumption is necessary. Electricity demand depends on various factors like temperature, everyday activities, time of day, days of the week days/Holidays. These parameters have led to price volatility and huge spikes in electricity prices. The research work proposes a short term Load prediction Model for LT2 (residential consumers), LT3 (Commercial Consumers) of Karnataka State Electricity Board using Cascaded Feed Forward Neural Network (CFNN). MATLAB software is utilized to design and test the forecasting model for predicting the power consumption. Furthermore, a shallow feed forward neural network-based prediction model is constructed and evaluated for performance comparison. The Performance metrics include Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE). The suggested STLF CFNN prediction model outperformed shallow feed forward networks on both performance metrics with prediction errors of less than 1%.

Deep learning based short term load forecasting with hybrid feature selection

The reliable and an economic operation of the power system rely on an accurate prediction of short term load. In this paper, a deep learning based Long Short Term Memory (LSTM) with hybrid feature selection namely RMR-HFS-LSTM, is proposed. The objective of this study is to reduce the curse of dimensionality, reduce the overfitting and improve the accuracy of short term load forecasting. The RMR-HFS is a combination of filter and wrapper feature selection introduced for identifying optimal subset of features. The instance based RReliefF and information theoretic based mutual information filter feature selection are utilized to reduce curse of dimensionality by finding and eliminating irrelevant features. The selected features of filter feature selection is tuned by using Recursive Feature Elimination (RFE) wrapper feature selection to reduce overfitting. The deep learning based LSTM improves the accuracy by handling uncertainty issues. The experiment was conducted on European weather and electricity load data using python on Tensorflow environment. The performance of the proposed RMR-HFS-LSTM model is compared against Multilayer Perceptron (MLP) and Recurrent Neural Network (RNN) in terms of Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The result shows that the proposed RMR-HFS-LSTM model outperforms other models.

Deep Learning based Load Forecasting with Decomposition and Feature Selection Techniques

The forecasting of short term electricity load plays a vital role in power system. It is essential for the power system's reliable, secure, and cost-effective functioning. This paper contributes significantly for enhancing the accuracy of short term electricity load forecasting. It presents a hybrid forecasting model called Gated Recurrent Unit with Ensemble Empirical Mode Decomposition and Boruta feature selection (EBGRU). It is a hybrid model that addresses the non-stationary, non-linearity and noisy issues of the time series input by using Ensemble Empirical Mode Decomposition (EEMD). It also addresses overfitting and curse of dimensionality issues of load forecasting by identifying the pertinent features using Boruta wrapper feature selection. It effectively handles the uncertainty and temporal dependency characteristics of load and forecasts the future load using deep learning based Gated Recurrent Unit (GRU). The proposed EBGRU model is experimented by using European and Australian Electricity load datasets. The temperature has high correlation with load demand. In this study, both load and temperature features are considered for the accurate short term load forecasting. The experimental outcome demonstrates that the proposed EBGRU model outperforms other deep learning models such as RNN, LSTM, GRU, RNN with EEMD and Boruta (EBRNN) and LSTM with EEMD and Boruta (EBLSTM).

Deep-learning-based short-term electricity load forecasting: A real case application

The rising popularity of deep learning can largely be attributed to the big data phenomenon, the surge in the development of new and novel deep neural network architectures, and the advent of powerful computational innovations. However, the application of deep neural networks is rare for time series problems when compared to other application areas. Short-term load forecasting, a typical and difficult time series problem, is considered as the application domain in this study. One-dimensional Convolutional Neural Networks (CNNs) use is rare in time series forecasting problems when compared to Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), and the efficiency of CNN has been rather remarkable for pattern extraction. Hence, a new method that uses one-dimensional CNNs based on Video Pixel Networks (VPNs) in this study, in which the gating mechanism of Multiplicative Units of the VPNs is modified in some sense, for short term load forecasting. Specifically, the proposed one-dimensional CNNs, LSTM and GRU variants are applied to real-world electricity load data for 1-hour-ahead and 24-hour-ahead prediction tasks which they are the main concerns for the electricity provider firms for short term load forecasting. Statistical tests were conducted to spot the significance of the performance differences in analyses for which ten ensemble predictions of each method were experimented. According to the results of the comparative analyses, the proposed one-dimensional CNN model yielded the best result in total with 2.21% mean absolute percentage error for 24-h ahead predicitions. On the other hand, not a noteworthy difference between the methods was spotted even the proposed one-dimensional CNN method yielded the best results with approximately 1% mean absolute percentage error for 1-h ahead predictions.

An Improved Model for Short Term load forecasting and Price Forecasting using Novel Machine learning for various areas of Lahore Pakistan

The economy relies on accurate projections of power usage. Accurate predictions of power consumption are essential for supply-side policymakers. In contrast, when there is a lack of data and considerations, it might be difficult to make accurate predictions. Consequently, using the original data sequence, we developed the DCOGM forecasting model, which combines data transformation with background value interpolation optimization (1,1). To test the accuracy of DCOGM (1,1) in simulation and prediction, two case studies are conducted. Most existing enhanced grey models do not do as well in forecasting as DCOGM (1,1) does, according to the data DCOGM is used to estimate Pakistan's Lahore City's overall energy consumption from 2017 to 2021. (1,1). According to the DCOGM (1,1) model, Lahore's demand for energy will increase over the next four years, comparing to those other grey adjustment models and the regular GM (1,1). It is possible to employ DCOGM (1,1) as a short-term forecasting approach in addition to other forecasting challenges with a limited number of data points.

Factors Impact Short Term Load Forecasting of Electric Vehicle Charging Station: A Case Study Considering Privacy Protection

Factors Impact Short Term Load Forecasting of Electric Vehicle Charging Station: A Case Study Considering Privacy Protection

A Data Driven Approach for Day Ahead Short Term Load Forecasting

This paper aims to develop an evolutionary deep learning based hybrid data driven approach for short term load forecasting (STLF) in the context of Bangladesh. With the lapse of time, the power system is getting complex. Penetration of intermittent renewable energy (RE) into the grid, changing prosumer load pattern with the need of demand side management (DSM) has thrown a challenge for dynamic power system operation and control. Load forecasting plays a significant role in this dynamic operation and control. In addition, it directly affects the future planning of network expansion, unit commitment and economic energy mix for power market. Day ahead short-term forecasting is very crucial for day to day operation. As such, various conventional and modified methods have been used over time for short-term prediction. Nevertheless, the existing approaches like age old statistical methods, artificial intelligence (AI), machine learning (ML), deep learning (DL) techniques alone cannot provide effective accuracy all the time. Hence, an integrated genetic algorithm (GA)-bidirectional gated recurrent unit (Bi-GRU) hybrid data driven technique (GA-BiGRU) is proposed in this work. The developed method is validated in Bangladesh power system (BPS) network by providing day ahead forecasting of electrical load of the whole country. Besides, the performance of the prediction model is compared with some existing approaches such as long short-term memory network (LSTM), gated recurrent unit (GRU) and integrated genetic algorithm-gated recurrent unit (GA-GRU) in terms of mean absolute performance error (MAPE) and root mean squared error (RMSE). The outcome gives an indication of better forecasting accuracy of proposed GA-BiGRU evolutionary DL technique compared to others.

A Novel Temporal Feature Selection Based LSTM Model for Electrical Short-Term Load Forecasting

An accurate electrical Short-term Load Forecasting (STLF) is an eminent factor in the power generation, electrical load dispatching and energy planning for the power supply companies, specifically in developing countries. This paper proposes a novel temporal feature selection-based Long Short-term Memory (LSTM) model developed by the combination of standard Artificial Neural Network (ANN) layer and LSTM for electrical short term load forecasting. The LSTM model has excellent capability of predicting the stochastic nature of an hour ahead electrical loads. The standard ANN layer consisting 11 neurons is used as an input to LSTM cells. Such a combination of ANN layer with LSTM was never proposed before. The proposed model accommodates variations in weather as well as temporal inputs like humidity, holidays, and date-time features in the hourly load data of the power supply company situated in Johor, Malaysia. This paper gives the insights of hyper parameter tuning to capture the more generalized electrical load patterns in the dataset without compromising the time complexity of the proposed model. The proposed approach was compared with five existing approaches, namely: ANN, LSTM model 1, LSTM model 2, LSTM model 3 and Convolutional Neural Network-LSTM (CNN-LSTM) using hourly load dataset of Johor. The experimental results demonstrate that the proposed approach outperformed the existing approaches in terms of root mean square error, mean absolute percentage error and Diebold-Mariano statistical inference test within 95% confidence interval.

Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost

Short term load forecasting is one of the important problems in power system. Accurate forecasting results can improve the flexibility of power market and resource utilization efficiency, which is of great significance to the efficient operation of power system.A short-term power load forecasting model based on feature selection and error correction is proposed to address the problems of low accuracy and weak generalization ability of short-term power load forecasting. The coarse set of features is firstly screened by using Maximal Information Coefficient (MIC), and then the fine set of key features affecting load forecasting is screened by using LightGBM and XGboost feature selection algorithms respectively. The corresponding fine set of features and historical loads are input into LightGBM and XGboost models with powerful prediction function for prediction, and use the predicted value to correct the error and complete the load prediction. Taking the actual data of a certain area in Northwest China as an example, the experimental results show that the proposed model has better prediction effect than other models.