Search

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. [ABSTRACT FROM AUTHOR]

Accurate electric load forecasting at various time periods is considered a necessary challenge for electricity consumers and generators to maximize their economic efficiency in energy markets. Hence, the accuracy and effectiveness of existing electric load forecasting approaches depends on the data quality. Nowadays, with the implementation of modern power systems and Internet of Things technology, forecasting models are faced with a large volume of data, which puts the security and health of data at risk due to the use of numerous measuring devices and the threat of cyber‐attackers. In this study, a cyber‐resilient hybrid deep learning‐based model is developed that accurately forecasts electric load in short‐term and long‐term time horizons. The architecture of the proposed model systematically integrates stacked multilayer denoising autoencoder (SMDAE) and generative adversarial network (GAN) and is called SMDAE‐GAN. In the proposed framework, SMDAE layer is used to pre‐process and remove real fs and intentional anomalies in data, and GAN layer is also utilized to forecast electric load values. The effectiveness of the SMDAE‐GAN structure is studied using realistic electrical load data monitored in the distribution network of Tabriz, Iran, and meteorological data measured in weather station there. Compared with other conventional load forecasting approaches, the developed framework has the highest accuracy in both cases of using normal data with real‐world noise and damaged data under false data injection attacks. [ABSTRACT FROM AUTHOR]

This study presents short-term electricity load forecasting for the New England area by processing initial data through correlation assessment and data clustering. This method is combined with artificial neural networks to improve accuracy and forecast performance. Data preprocessing focuses on two main issues: identifying correlations between variables to eliminate less relevant factors and retaining highly correlated variables to reduce noise, as well as reducing the data sample size before training the neural network. This evaluation aims to determine the factors that have a significant impact on electricity load. These factors can include previous load values, weather conditions, time, types of electricity usage, and others. This technique ensures that reducing the size in both dimensions of the large dataset does not result in the loss of critical information, maintaining the accuracy of computational programs and the performance of neural network training at high levels. The neural network is trained to classify and cluster data based on previously identified correlated characteristics. As a result, the forecasting model can make more accurate predictions about future electricity loads. Experimental results show that the proposed method achieved more than 97 % accuracy, outperforming traditional methods in both speed and load forecasting accuracy. The new dataset had 63% fewer samples compared to the initial dataset. [ABSTRACT FROM AUTHOR]

Electric load forecasting plays a vital role in all aspects of the electrical system, including generation, transmission, distribution, and electricity retail. The LightGBM ensemble learning method has been widely applied in load forecasting and has yielded many positive results. This study presents an algorithm combining the grid space of hyperparameters with cross-validation to evaluate the accuracy of LightGBM models across different hyperparameter values. Peak load data from Ho Chi Minh City were used to enhance the reliability of the results. Analysis of the results based on boxplot statistical charts indicated that the accuracy of the LightGBM model significantly depends on the hyperparameter values. Moreover, using default hyperparameter values may result in large errors in load forecasting. [ABSTRACT FROM AUTHOR]

With the global objectives of achieving a "carbon peak" and "carbon neutrality" along with the implementation of carbon reduction policies, China's industrial structure has undergone significant adjustments, resulting in constraints on high-energy consumption and high-emission industries while promoting the rapid growth of green industries. Consequently, these changes have led to an increasingly complex power system structure and presented new challenges for electricity demand forecasting. To address this issue, this study proposes a 24-step multivariate time series short-term load forecasting algorithm model based on KNN data imputation and BiTCN bidirectional temporal convolutional networks combined with BiGRU bidirectional gated recurrent units and attention mechanism. The Kepler adaptive optimization algorithm (KOA) is employed for hyperparameter optimization to effectively enhance prediction accuracy. Furthermore, using real load data from a wind farm in Xinjiang as an example, this paper predicts the electricity load from 1 January to 30 December in 2019. Experimental results demonstrate that our comprehensive short-term load forecasting model exhibits lower prediction errors and superior performance compared to traditional methods, thus holding great value for practical applications. [ABSTRACT FROM AUTHOR]

Accurate load forecasting is essential for the efficient and reliable operation of power systems. Traditional models primarily utilize unidirectional data reading, capturing dependencies from past to future. This paper proposes a novel approach that enhances load forecasting accuracy by fine tuning an attention-based model with a bidirectional reading of time-series data. By incorporating both forward and backward temporal dependencies, the model gains a more comprehensive understanding of consumption patterns, leading to improved performance. We present a mathematical framework supporting this approach, demonstrating its potential to reduce forecasting errors and improve robustness. Experimental results on real-world load datasets indicate that our bidirectional model outperforms state-of-the-art conventional unidirectional models, providing a more reliable tool for short and medium-term load forecasting. This research highlights the importance of bidirectional context in time-series forecasting and its practical implications for grid stability, economic efficiency, and resource planning. [ABSTRACT FROM AUTHOR]

Dynamic load forecasting is essential for effective energy management and grid operation. The use of GRU (Gated Recurrent Unit) and Long Short-Term Memory (LSTM) networks for precise load prediction is investigated in this paper. This research examines dynamic load patterns by innovatively integrating heterogeneous information from several datasets. The results show that the LSTM and GRU models are equally good at making predictions and that this holds true across a variety of datasets. Furthermore, the models' ability to accurately capture the temporal relationships in the load data is demonstrated by their low Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE) values. Additionally, the comparative analysis results, which highlight flexibility in model selection, can aid energy sector decision makers. The significance of precise load projections for maintaining grid dependability and optimizing resources is further highlighted by this work, which also elucidates the effects of forecast inaccuracies on decision-making procedures. Our research study provides important information for power system management strategy planning, which in turn promotes the continuous innovation of smart grids in dynamic load forecasting to keep up with changing energy consumption patterns. [ABSTRACT FROM AUTHOR]

Accurate and reliable medium- and long-term load forecasting is crucial for the rational planning and operation of power systems. However, existing methods often struggle to accurately extract and capture long-term dependencies in load data, leading to poor predictive accuracy. Therefore, this paper proposes a medium- and long-term residential load forecasting method based on FEDformer, aiming to capture long-term temporal dependencies of load data in the frequency domain while considering factors such as electricity prices and temperature, ultimately improving the accuracy of medium- and long-term load forecasting. The proposed model employs Discrete Cosine Transform (DCT) for frequency domain transformation of time-series data to address the Gibbs phenomenon caused by the use of Discrete Fourier Transform (DFT) in FEDformer. Additionally, causal convolution and attention mechanisms are applied in the frequency domain to enhance the model's capability to capture long-term dependencies. The model is evaluated using real-world load data from power systems, and experimental results demonstrate that the proposed model effectively learns the temporal and nonlinear characteristics of load data. Compared to other baseline models, DCTformer improves prediction accuracy by 37.5% in terms of MSE, 26.9% in terms of MAE, and 26.24% in terms of RMSE. [ABSTRACT FROM AUTHOR]

To accommodate the rapid development of the distribution network of China, it is essential to research load forecasting methods with higher accuracy and stronger generalization capabilities in order to optimize distribution system control strategies, ensure the efficient and reliable operation of the power system, and provide a stable power supply to users. In this paper, a short-term load forecasting method is proposed for low-voltage distribution substations based on the bidirectional long short-term memory (BiLSTM) model. First, principal component analysis (PCA) and the fuzzy C-means method based on a genetic algorithm (GA-FCM) are used to extract the main influencing factors and classify different types of user electricity consumption behaviors. Then, the BiLSTM forecasting model utilizing the stochastic weight averaging (SWA) algorithm to enhance generalization capability is constructed. Finally, the load data from a low-voltage distribution substation in China over recent years are selected as a case study. Compared with conventional LSTM and BiLSTM prediction models, the annual electricity load curves for various user types forecasted by the PCA-BiLSTM model are more closely aligned with actual data curves. The proposed BiLSTM forecasting model exhibits higher accuracy and can forecast user electricity consumption data that more accurately reflect real-life usage. [ABSTRACT FROM AUTHOR]

For the air conditioning with secondary pump variable flow system, considering the regional cooling situation, the multi-objective regression method was used to solve the load forecasting problem for improving the accuracy of load forecasting. For the central air conditioning, two multi-objective regression load forecasting models of multi-objective support vector regression(SVR) and multi-objective long short-term memory(LSTM)neural network were proposed. The two models were used to train and predict on the data of the secondary pump variable flow system of the hospital in Shanghai, and the results were compared with those of the single objective regression prediction model. The results show that the prediction accuracies of the two multi-objective prediction models are higher than that of the single objective regression prediction model, and the multi-objective SVR load forecasting model has higher prediction accuracy than the multi-objective LSTM load forecasting model. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is critical for power system planning and operations, and ensemble forecasting methods for electricity loads have been shown to be effective in obtaining accurate forecasts. However, the weights in ensemble prediction models are usually preset based on the overall performance after training, which prevents the model from adapting in the face of different scenarios, limiting the improvement of prediction performance. In order to improve the accurateness and validity of the ensemble prediction method further, this paper proposes an ensemble deep reinforcement learning approach using Q‐learning dynamic weight assignment to consider local behaviours caused by changes in the external environment. Firstly, the variational mode decomposition is used to reduce the non‐stationarity of the original data by decomposing the load sequence. Then, the recurrent neural network (RNN), long short‐term memory (LSTM), and gated recurrent unit (GRU) are selected as the basic power load predictors. Finally, the optimal weights are ensembled for the three sub‐predictors by the optimal weights generated using the Q‐learning algorithm, and the final results are obtained by combining their respective predictions. The results show that the forecasting capability of the proposed method outperforms all sub‐models and several baseline ensemble forecasting methods. [ABSTRACT FROM AUTHOR]

Recent economic growth and development have considerably raised energy consumption over the globe. Electric load prediction approaches become essential for effective planning, decision-making, and contract evaluation of the power systems. In order to achieve effective forecasting outcomes with minimum computation time, this study develops an improved whale optimization with deep learning enabled load prediction (IWO-DLELP) scheme for energy storage systems (ESS) in smart grid platform. The major intention of the IWO-DLELP technique is to effectually forecast the electric load in SG environment for designing proficient ESS. The proposed IWO-DLELP model initially undergoes pre-processing in two stages namely min-max normalization and feature selection. Besides, partition clustering approach is applied for the decomposition of data into distinct clusters with respect to distance and objective functions. Moreover, IWO with bidirectional gated recurrent unit (BiGRU) model is applied for the prediction of load and the hyperparameters are tuned by the use of IWO algorithm. The experiment analysis reported the enhanced results of the IWO-DLELP model over the recent methods interms of distinct evaluation measures. [ABSTRACT FROM AUTHOR]

Numerous studies on short‐term load forecasting (STLF) have used feature extraction methods to increase the model's accuracy by incorporating multidimensional features containing time, weather and distance information. However, less attention has been paid to the input data size and output dimensions in STLF. To address these two issues, an STLF model is proposed based on output dimensions using only load data. First, the load data's long‐term behavior (trend and seasonality) is extracted through the long short‐term memory network (LSTM), followed by convolution to obtain the load data's non‐stationarity. Then, using the self‐attention mechanism (SAM), the crucial input load information is emphasized in the forecasting process. The calculation example shows that the proposed algorithm outperforms LSTM, LSTM‐based SAM, and CNN‐GRU‐based SAM by more than 10% in eight different buildings, demonstrating its suitability for forecasting with only load data. Additionally, compared to earlier research utilizing two well‐known public data sets, the MAPE is optimized by 2.2% and 5%, respectively. Also, the method has good prediction accuracy for a wide variety of time granularities and load aggregation levels, so it can be applied to various load forecasting scenarios and has good reference significance for load forecasting instrumentation. [ABSTRACT FROM AUTHOR]

In a real-world scenario of load forecasting, it is crucial to determine the energy consumption in electrical networks. The energy consumption data exhibit high variability between historical data and newly arriving data streams. To keep the forecasting models updated with the current trends, it is important to fine-tune the models in a timely manner. This article proposes a reliable inductive transfer learning (ITL) method, to use the knowledge from existing deep learning (DL) load forecasting models, to innovatively develop highly accurate ITL models at a large number of other distribution nodes reducing model training time. The outlier-insensitive clustering-based technique is adopted to group similar distribution nodes into clusters. ITL is considered in the setting of homogeneous inductive transfer. To solve overfitting that exists with ITL, a novel weight regularized optimization approach is implemented. The proposed novel cross-model methodology is evaluated on a real-world case study of 1000 distribution nodes of an electrical grid for one-day ahead hourly forecasting. Experimental results demonstrate that overfitting and negative learning in ITL can be avoided by the dissociated weight regularization (DWR) optimizer and that the proposed methodology delivers a reduction in training time by almost 85.6% and has no noticeable accuracy losses. [ABSTRACT FROM AUTHOR]

Forecasting the electrical load is essential in power system design and growth. It is critical from both a technical and a financial standpoint as it improves the power system performance, reliability, safety, and stability as well as lowers operating costs. The main aim of this paper is to make forecasting models to accurately estimate the electrical load based on the measurements of current electrical loads of the electricity company. The importance of having forecasting models is in predicting the future electrical loads, which will lead to reducing costs and resources, as well as better electric load distribution for electric companies. In this paper, deep learning algorithms are used to forecast the electrical loads; namely: (1) Long Short-Term Memory (LSTM), (2) Gated Recurrent Units (GRU), and (3) Recurrent Neural Networks (RNN). The models were tested, and the GRU model achieved the best performance in terms of accuracy and the lowest error. Results show that the GRU model achieved an R-squared of 90.228%, Mean Square Error (MSE) of 0.00215, and Mean Absolute Error (MAE) of 0.03266. [ABSTRACT FROM AUTHOR]

The energy Internet (EI) equipment may face threats that attackers poison federated learning (FL) models to disturb electricity load forecasting. To mitigate this vulnerability, it is important to study load forecasting disturbance approaches. This article proposes a side-channel analysis (SCA)-based disturbance approach. First, we design an FL SCA scheme to extract power information from the FL chip running forecasting model. Second, we propose an FL data speculation method using an optimized convolutional neural network trained with SCA information. Third, we design a label-flipping-based poisoning scheme with speculated data characteristics for load forecasting disturbance. Experimental results show attackers can successfully poison and disturb FL-based load forecasting. The average accuracy of EI load data speculation is 99.8%. This work is the first to study EI load forecasting disturbance from an SCA perspective. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is an important prerequisite for smart grid controls. The current methods are mainly based on the convolution neural network (CNN) or long short-term memory (LSTM) model to realize load forecasting. For the multi-factor input sequence, the existing methods cannot obtain multi-scale features of the time series and the important parameters of the multi-factor, resulting in low accuracy and robustness. To address these problems, a multi-scale feature attention hybrid network is proposed, which uses LSTM to extract the time correlation of the sequence and multi-scale CNN to automatically extract the multi-scale feature of the load. This work realizes the integration of features by constructing a circular network. In the proposed model, a two-branch attention mechanism is further constructed to capture the important parameters of different influencing factors to improve the model's robustness, which can make the network to obtain effective features at the curve changes. Comparative experiments on two open test sets show that the proposed multi-scale feature attention mixture network can achieve accurate short-term load forecasting and is superior to the existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiao Tong University (1006-2467) is the property of Journal of Shanghai Jiao Tong University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

In order to effectively carry out the heavy overload monitoring and maintenance of public transformers in the distribution network, ensure the reliability of the distribution network power supply, and improve customer satisfaction with electricity consumption, this paper presents a short-term heavy overload forecasting method for public transformers based on the LSTM-XGBOOST combined model. The model extracts heavy overload feature variables from four dimensions, including basic parameter information, weather, time, and recent load, and constructs a short-term second highest load prediction model based on the LSTM algorithm to obtain the predicted value of the second highest load rate. After aggregating the heavy overload feature variables and the predicted second highest load rate, the XGboost algorithm is employed to construct a short-term heavy overload prediction model for public transformers to judge whether the public transformers display heavy overload. The test results show that this method has high accuracy in short-term heavy overload forecasting, and can effectively assist in the key monitoring and control of heavy overload in public transformers. [ABSTRACT FROM AUTHOR]

This paper proposes a new optimized Deep Learning (DL) network design for time series load forecasting. At first, DL's hyper parameters are optimized using the Levy flight-particle swarm optimization (LF-PSO) technique; then, the optimized DL model is used for load prediction. Furthermore, the results are compared with the existing state-of-the-art techniques to show prediction accuracy. Experiment and measured values indicate that the proposed new DL model is highly efficient for load prediction. [ABSTRACT FROM AUTHOR]

Nowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns of electric load. Since there are large fluctuations in both electricity production and use, it is a difficult task to achieve a balance between electric load and demand. By analyzing past electric consumption records to estimate the upcoming electricity load, the issue of fluctuating behavior can be resolved. In this study, a framework for feature selection, extraction, and regression is put forward to carry out the electric load prediction. The feature selection phase uses a combination of extreme gradient boosting (XGB) and random forest (RF) to determine the significance of each feature. Redundant features in the feature extraction approach are removed by applying recursive feature elimination (RFE). We propose an enhanced support vector machine (ESVM) and an enhanced convolutional neural network (ECNN) for the regression component. Hyperparameters of both the proposed approaches are set using the random search (RS) technique. To illustrate the effectiveness of our proposed strategies, a comparison is also performed between the state-of-the-art approaches and our proposed techniques. In addition, we perform statistical analyses to prove the significance of our proposed approaches. Simulation findings illustrate that our proposed approaches ECNN and ESVM achieve higher accuracies of 98.83% and 98.7%, respectively. [ABSTRACT FROM AUTHOR]

Smart grid is an advanced electrical grid that enables more efficient distribution of electricity. It counters many of the problems presented by renewable energy sources such as variability in production through techniques like load forecasting and dynamic pricing. Smart grid generates massive amounts of data through smart meters, this data is used to forecast future load to adjust distribution. To process all this data, big data analysis is necessary. Most existing schemes use Apache Hadoop for big data processing and various techniques for load forecasting that include methods based on statistical theory, machine learning and deep learning. This paper proposes using Apache Spark for big data analysis and a modified version of the transformer model for forecasting load profiles of households. The modified transformer model has been tested against several state-of-the-art machine learning models. The proposed scheme was tested against several baseline and state-of-the-art machine learning models and evaluated in terms of the RMSE, MAE, MedAE and R2 scores. The obtained results show that the proposed model has better performance in terms of RMSE and R2 which are the preferred metrics when evaluating a regression model on data with a large number of outliers. [ABSTRACT FROM AUTHOR]

In this paper, a Median Grid Search algorithm based on the median values is proposed to develop a more accurate algorithm used to investigate the optimal hyperparameter of the SVR model for load forecasting. In addition, the methodology to benchmark the proposed Grid Search and the conventional Grid Search is built and sufficiently utilized. The data gathered from the South Australia state, Australia and Ho Chi Minh City load demands are used in experiments. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithm. [ABSTRACT FROM AUTHOR]

The introduction of advanced metering infrastructure (AMI) smart meters has given rise to fine-grained electricity usage data at different levels of time granularity. AMI collects high-frequency daily energy consumption data that enables utility companies and data aggregators to perform a rich set of grid operations such as demand response, grid monitoring, load forecasting and many more. However, the privacy concerns associated with daily energy consumption data has been raised. Existing studies on data anonymization for smart grid data focused on the direct application of perturbation algorithms, such as microaggregation, to protect the privacy of consumers. In this paper, we empirically show that reliance on microaggregation alone is not sufficient to protect smart grid data. Therefore, we propose DFTMicroagg algorithm that provides a dual level of perturbation to improve privacy. The algorithm leverages the benefits of discrete Fourier transform (DFT) and microaggregation to provide additional layer of protection. We evaluated our algorithm on two publicly available smart grid datasets with millions of smart meters readings. Experimental results based on clustering analysis using k-Means, classification via k-nearest neighbor (kNN) algorithm and mean hourly energy consumption forecast using Seasonal Auto-Regressive Integrated Moving Average with eXogenous (SARIMAX) factors model further proved the applicability of the proposed method. Our approach provides utility companies with more flexibility to control the level of protection for their published energy data. [ABSTRACT FROM AUTHOR]

In order to realize short-time load forecasting, an Adaboost-BP method with a weight update mechanism is proposed based on ensemble learning theory. Firstly, the original historical load power is decomposed into a set of sub-series with diverse characteristics via using ensemble empirical mode decomposition. Then, BP neural network is performed as a weak learner to predict the load power of test samples. At the same time, the prediction results are used to update the weight of the weak learner and test sample and then construct a strong learner to obtain the final prediction results. According to the analysis results of the characteristics of each sub-series, the load forecasting model is established. The result of analysing the calculation example shows that the proposed prediction model outperforms all other algorithms in accuracy, which has high engineering application value. [ABSTRACT FROM AUTHOR]

Accurate forecasting of natural gas load forecasting is of great practical significance to balance supply and demand of gas system. Load forecasting is categorized in long-term, mid-term and short-term. Among them, mid-term load forecasting that monitors monthly operations is of decisive significance to urban gas pipe network planning, gas engineering project construction and design. In this study, we adopt Prophet model that reflects the seasonal fluctuations and holidays influence to forecasting the monthly gas load of urban gas and compare the results with the other two forecasting methods such as autoregressive integrated moving average model (ARIMA) and exponential smoothing prediction method (ESM). The models were trained and tested on gas consumption data gathered in one central city in China from 2017 to 2021. The result shows that an increasing trend with an average growth rate between 10% and 20% year by year, a decreasing trend at an average rate of 14.9% on legal holiday. According to this study, the Prophet model has an excellent performance in monthly natural gas forecasting. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting is the key foundation and important premise of urban power system planning. Considering that urban power load demand is closely related to economic development and meteorological conditions, and with the application and promotion of various energy coupling equipment and the promotion of electric energy substitution policy, the relationship between gas load and power load demand is increasing. However, most of the existing load forecasting methods only consider a single economic factor or a single meteorological factor, and fail to combine the coupling and complementarity between loads. Based on this, this paper first analyzes the coupling characteristics between power load and urban economic, meteorological, and gas load with Copula theory; Secondly, the key parameters of the least squares support vector machine (LSSVM) are solved by using the salp swarm algorithm (SSA), and the urban monthly power load forecasting model based on SSA-LSSVM is established; Finally, based on the macroeconomic data, meteorological observation data and monthly electrical load of a city in North China, the prediction model is verified. Through comparison with different prediction scenarios, it is confirmed that the built model can effectively improve the prediction accuracy and has good application effects. [ABSTRACT FROM AUTHOR]

As the access to consumption data available in household smart meters is now very common in several developed countries, this kind of information is assuming a providential role for different players in the energy sector. The proposed study was applied to data available from the Smart Meter Energy Consumption Data in the London Households dataset, provided by UK Power Networks, containing half-hourly readings from an original sample of 5567 households (71 households were hereby carefully selected after a justified filtering process). The main aim is to forecast the day—ahead load profile, based only on previous load values and some auxiliary variables. During this research different forecasting models are applied, tested and compared to allow comprehensive analyses integrating forecasting accuracy, processing times and the interpretation of the most influential features in each case. The selected models are based on Multivariate Adaptive Regression Splines, Random Forests and Artificial Neural Networks, and the accuracies resulted from each model are compared and confronted with a baseline (Naïve model). The different forecasting approaches being evaluated have been revealed to be effective, ensuring a mean reduction of 15% in Mean Absolute Error when compared to the baseline. Artificial Neural Networks proved to be the most accurate model for a major part of the residential consumers. [ABSTRACT FROM AUTHOR]

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, singlearea, 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. [ABSTRACT FROM AUTHOR]

Increased focus on sustainability and energy decentralization has positively impacted the adoption of nanogrids. With the tremendous growth, load forecasting has become crucial for their daily operation. Since the loads of nanogrids have large variations with sudden usage of large household electrical appliances, existing forecasting models, majorly focused on lower volatile loads, may not work well. Moreover, abrupt operation of electrical appliances in a nanogrid, even for shorter durations, especially in "Peak Hours", raises the energy cost substantially. In this paper, an ANN model with dynamic feature selection is developed to predict the hour-ahead load of nanogrids based on meteorological data and a load lag of 1 h (t-1). In addition, by thresholding the predicted load against the average load of previous hours, peak loads, and their time indices are accurately identified. Numerical testing results show that the developed model can predict loads of nanogrids with the Mean Square Error (MSE) of 0.03 KW, the Mean Absolute Percentage Error (MAPE) of 9%, and the coefficient of variation (CV) of 11.9% and results in an average of 20% daily energy cost savings by shifting peak load to off-peak hours. [ABSTRACT FROM AUTHOR]

This paper projects the risk associated with social benefit gained by Independent System Operator (ISO) due to unpredictability of load demand and intermittent nature of Renewable Energy Sources (RES). The hybrid method i.e. Wavelet Transform–Auto Regression Integrated Moving Average (WT-ARIMA) is used for forecasting the load in day-ahead market. The load demand for 24 hours is forecasted using the historical hourly data of 2 months. The mean absolute percentage error (MAPE) is calculated for both classical ARIMA and WT-ARIMA model. When compared to the ARIMA model, the WT-ARIMA model has a better fit to the time series data. This paper relates the load forecasting with energy market and shows the impact of forecasting error on market parameters. The system parameters like generation cost, social benefit and power loss are analyzed in day-ahead and real-time market. This work also elaborates the effect of intermittent nature of RES on the system parameters. The optimal location of RES based distributed generation is identified by higher Locational Marginal Price (LMP) based ranking method. The optimal energy management problem is formulated with the aim to minimize the total generation cost taking into account the variability in wind power and solar power. The uncertainty modeling of wind and solar is projected by the Rayleigh and Beta distribution respectively. The risk associated with social benefit of ISO due to uncertainty of wind and solar is calculated using indices, Value at Risk and Conditional Value at Risk. The proposed approach is implemented on IEEE 30 bus system. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Dalian University of Technology / Dalian Ligong Daxue Xuebao is the property of Journal of Dalian University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the Smart Grid (SG) residential environment, consumers change their power consumption routine according to the price and incentives announced by the utility, which causes the prices to deviate from the initial pattern. Thereby, electricity demand and price forecasting play a significant role and can help in terms of reliability and sustainability. Due to the massive amount of data, big data analytics for forecasting becomes a hot topic in the SG domain. In this paper, the changing and non-linearity of consumer consumption pattern complex data is taken as input. To minimize the computational cost and complexity of the data, the average of the feature engineering approaches includes: Recursive Feature Eliminator (RFE), Extreme Gradient Boosting (XGboost), Random Forest (RF), and are upgraded to extract the most relevant and significant features. To this end, we have proposed the DensetNet-121 network and Support Vector Machine (SVM) ensemble with Aquila Optimizer (AO) to ensure adaptability and handle the complexity of data in the classification. Further, the AO method helps to tune the parameters of DensNet (121 layers) and SVM, which achieves less training loss, computational time, minimized overfitting problems and more training/test accuracy. Performance evaluation metrics and statistical analysis validate the proposed model results are better than the benchmark schemes. Our proposed method has achieved a minimal value of the Mean Average Percentage Error (MAPE) rate i.e., 8% by DenseNet-AO and 6% by SVM-AO and the maximum accurateness rate of 92% and 95%, respectively. [ABSTRACT FROM AUTHOR]

This article presents hourly load forecasting by using an incremental learning model called Online Sequential Extreme Learning Machine (OSELM), which can learn and adapt automatically according to new arrival input. However, the use of OS-ELM requires a sufficient amount of initial training sample data, which makes OS-ELM inoperable if sufficiently accurate sample data cannot be obtained. To solve this problem, a synthesis of the initial training sample is proposed. The synthesis of the initial sample is achieved by taking the first data received at the start of working and adding random noises to that data to create new and sufficient samples. Then the synthesis samples are used to initial train the OS-ELM. This proposed method is compared with Fully Online Extreme Learning Machine (FOS-ELM), which is an incremental learning model that also does not require the initial training samples. Both the proposed method and FOS-ELM are used for hourly load forecasting from the Hourly Energy Consumption dataset. Experiments have shown that the proposed method with a wide range of noise levels, can forecast hourly load more accurately than the FOS-ELM. [ABSTRACT FROM AUTHOR]

Maintaining stability and control over the electric system requires increasing information about the consumers' profiling due to changes in the form of electricity generation and consumption. To overcome this trouble, short-term load forecasting (STLF) on individual consumers gained importance in the last years. Nonetheless, predicting the profile of an individual consumer is a difficult task. The main challenge lies in the uncertainty related to the individual consumption profile, which increases forecasting errors. Thus, this paper aims to implement a load predictive model focused on individual consumers taking into account its randomness. For this purpose, a methodology is proposed to determine and select predictive features for individual STLF. The load forecasting of an individual consumer is simulated based on the four main machine learning techniques used in the literature. A 2.73% reduction in the forecast error is obtained after the correct selection of the predictive features. Compared to the baseline model (persistent forecasting method), the error is reduced by up to 19.8%. Among the techniques analyzed, support vector regression (SVR) showed the smallest errors (8.88% and 9.31%). [ABSTRACT FROM AUTHOR]

Load forecasting is a procedure of fundamental importance in power systems operation and planning. Many entities can benefit from accurate load forecasting such as generation companies, systems operators, retailers, prosumers, and others. A variety of models have been proposed so far in the literature. Among them, artificial neural networks are a favorable approach mainly due to their potential for capturing the relationship between load and other parameters. The forecasting performance highly depends on the number and types of inputs. The present paper presents a particle swarm optimization (PSO) two-step method for increasing the performance of short-term load forecasting (STLF). During the first step, PSO is applied to derive the optimal types of inputs for a neural network. Next, PSO is applied again so that the available training data is split into homogeneous clusters. For each cluster, a different neural network is utilized. Experimental results verify the robustness of the proposed approach in a bus load forecasting problem. Also, the proposed algorithm is checked on a load profiling problem where it outperforms the most common algorithms of the load profiling-related literature. During input selection, the weights update is held in asymmetrical duration. The weights of the training phase require more time compared with the test phase. [ABSTRACT FROM AUTHOR]

Short-term electric power load forecasting is a critical and essential task for utilities in the electric power industry for proper energy trading, which enables the independent system operator to operate the network without any technical and economical issues. From an electric power distribution system point of view, accurate load forecasting is essential for proper planning and operation. In order to build most robust machine learning model to forecast the load with a good accuracy irrespective of weather condition and type of day, features such as the season, temperature, humidity and day-status are incorporated into the data. In this paper, a machine learning model, namely a regression tree, is used to forecast the active power load an hour and one day ahead. Real-time active power load data to train and test the machine learning models are collected from a 33/11 kV substation located in Telangana State, India. Based on the simulation results, it is observed that the regression tree model is able to forecast the load with less error. [ABSTRACT FROM AUTHOR]

In recent years, support vector regression (SVR) models have been widely applied in short-term electricity load forecasting. A critical challenge when applying the SVR model is to determine the model for optimal hyperparameters, which can be solved using several optimization methods as the grid search algorithm. Another challenge that affects the response time and the precision of the SVR model is the normalization process of input data. In this paper, the grid search algorithm will be suggested based on data normalization methods including Z-score, min-max, max, decimal, sigmoidal, softmax, and then utilized to evaluate both the response time and precision. To verify the proposed methods, the actual electricity load demand data of two cities, including Queensland of Australia and Ho Chi Minh City of Vietnam, were utilized in this study. [ABSTRACT FROM AUTHOR]

Smart Grids (SG) generate extensive data sets regarding the system variables, viz., and demand and supply. These extremely large data sets are known as big data. Hence, preprocessing of this vast data and integration become critical steps in the load forecasting process. The precise prediction of the load is the primary concern while balancing the demand and supply in SG. Many techniques were devised for load forecasting using machine learning methods such as Deep-learning Models. However, in the case of large data sets, only a few models provide good performance, viz. Autoregressive Integrated Moving Average (ARIMA). However, this approach is complex, as it takes a minimum of 50 observations to make an evaluation. In this paper, the Prophet technique is used in the prediction of future demand response based on the past data, which is in the form of a time series. This technique is valid even if a few values in the time series are not available. Furthermore, the procedure is not affected by fluctuations, trends, and abnormal variations. The automatic model fitting approach is adopted for its effective performance. Further, ARIMA and Prophet model have been used to forecast and the approach is verified using various evaluation metrics. The demand response management was achieved and is being validated with two data sets. The results show the effectiveness of the Prophet model in the demand response management scheme involving large data sets. [ABSTRACT FROM AUTHOR]

This letter proposes a transferrable model-agnostic meta-learning (T-MAML) approach for short-term load forecasting for single households. The proposed approach enables multiple households to collaboratively train a generic artificial neural network (ANN) model. The generic ANN model is then further trained at each target household node for the STLF purpose. The proposed T-MAML based STLF approach is featured by: (1) significant reduction of computation and communication costs on the household side; and (2) superior STLF performance, especially when there is limited load data for training in a target household. Experiments based on a real Australian residential dataset are conducted to validate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

In recent years, a large variety of short-term load forecasting methodologies have been proposed, but a common drawback of them is that require a large amount of historical data to train the model. However, in reality, the cases in limited historical data would be more frequently occurred, for example, a new house or substation is built. To tackle this issue, a combining forecasting method of deep residual neural network (ResNet)-based transfer learning for residential loads is proposed in this article. To improve the accuracy and reliability of transfer learning, a novel deep ResNet with dual skip connections (ResNet-DSC) is proposed as the base model. Then with sparse training data, a Bayesian probability weighted averaging (approach is proposed, to address the model combination parameters estimation problem. In addition, probability density function forecasting is also delivered by the method. For demonstration, a series of experiments, with actual residential load data, was performed. With the comparison with other transfer learning and nontransfer learning approaches, the effectiveness and improvement of the proposed method have been validated. [ABSTRACT FROM AUTHOR]

Developing an appropriate model for accurate prediction of energy consumption is very essential for developing an effective energy management system for residential buildings. In view of this, the Short-term Load Forecasting (STLF) of household appliances has been performing an important role in supervising and managing energy in the residential community. In the domain of big data analytics, data-driven load forecasting approaches have realized an amazing performance in the recognition of patterns of residential electric loads and forecasting energy consumption. Nevertheless, current research emphasizes the use of powerful feature-engineering methods, which are ineffective and result in low generalization performance. Further, considering the differences in the consumption behavior of various home appliances, it is unfeasible to discover energy consumption characteristics physically in the power system. Thus, this study addresses the problems of STLF using a novel two-stream deep learning (DL) model called STLF-Net. The first stream is designed with Gated Recurrent Units (GRUs) to learn and capture the long-term temporal representations of the energy utilization data. Simultaneously, in the second stream, the short-term information and positional representations are modeled using a stack of temporal convolutional (TC) modules. The TC module is designated using dilated causal convolutions and residual connection to enable efficient feature extraction while alleviating the gradient vanishing issues. The learned representations from the two streams are fused and subsequently passed to several dense layers to generate the final hour-ahead load forecasts. Experimental assessments on two public energy consumption predictions datasets (IHEPC and AEP) demonstrated the superior performance of the STLF-Net over the recent cutting-edge data-driven approaches. [ABSTRACT FROM AUTHOR]

Smart Grid (S.G.) is a digitally enabled power grid with an automatic capability to control electricity and information between utility and consumer. S.G. data streams are heterogenous and possess a dynamic environment, whereas the existing machine learning methods are static and stand obsolete in such environments. Since these models cannot handle variations posed by S.G. and utilities with different generation modalities (D.G.M.), a model with adaptive features must comply with the requirements and fulfill the demand for new data, features, and modality. In this study, we considered two open sources and one real-world dataset and observed the behavior of ARIMA, ANN, and LSTM concerning changes in input parameters. It was found that no model observed the change in input parameters until it was manually introduced. It was observed that considered models experienced performance degradation and deterioration from 5 to 15% in terms of accuracy relating to parameter change. Therefore, to improve the model accuracy and adapt the parametric variations, which are dynamic in nature and evident in S.G. and D.G.M. environments. The study has proposed a novel adaptive framework to overcome the existing limitations in electrical load forecasting models. [ABSTRACT FROM AUTHOR]

To address the current difficulties and problems of short-term load forecasting (STLF), this paper proposes a combined forecasting method based on the improved sparrow search algorithm (ISSA), with fused Cauchy mutation and opposition-based learning (OBL), to optimize the hyperparameters of the long- and short-term-memory (LSTM) network. For the sparrow-search algorithm (SSA), a Sin-chaotic-initialization population, with an infinite number of mapping folds, is first used to lay the foundation for global search. Secondly, the previous-generation global-optimal solution is introduced in the discoverer-location update way, to improve the adequacy of the global search, while adaptive weights are added to reconcile the ability of the local exploitation and global search of the algorithm as well as to hasten the speed of convergence. Then, fusing the Cauchy mutation arithmetic and the OBL strategy, a perturbation mutation is performed at the optimal solution position to generate a new solution, which, in turn, strengthens the ability of the algorithm to get rid of the local space. After that, the ISSA-LSTM forecasting model is constructed, and the example is verified based on the power load data of a region, while the experimental comparison with various algorithms is conducted, and the results confirm the superiority of the ISSA-LSTM model. [ABSTRACT FROM AUTHOR]

To extract strong correlations between different energy loads and improve the interpretability and accuracy for load forecasting of a regional integrated energy system (RIES), an explainable framework for load forecasting of an RIES is proposed. This includes the load forecasting model of RIES and its interpretation. A coupled feature extracting strategy is adopted to construct coupled features between loads as the input variables of the model. It is designed based on multi-task learning (MTL) with a long short-term memory (LSTM) model as the sharing layer. Based on SHapley Additive exPlanations (SHAP), this explainable framework combines global and local interpretations to improve the interpretability of load forecasting of the RIES. In addition, an input variable selection strategy based on the global SHAP value is proposed to select input feature variables of the model. A case study is given to verify the effectiveness of the proposed model, constructed coupled features, and input variable selection strategy. The results show that the explainable framework intuitively improves the interpretability of the prediction model. [ABSTRACT FROM AUTHOR]

Household electricity consumption has been rising gradually with the improvement of living standards. Making short-term load forecasting at the small-scale users plays an increasingly important role in the future power network planning and operation. To meet the efficiency of the dispatching system and the demand of human daily power consumption, an optimal forecasting model Attention-CNN-GRU of small-scale users load at various periods of the day based on family behavior pattern recognition is proposed in this study. The low-level data information (smart meter data) is used to build the high-level model (small-scale users load). Attention mechanism and convolutional neural networks (CNN) can further enhance the prediction accuracy of gated recurrent unit (GRU) and notably shorten its prediction time. The recognition of family behavior patterns can be achieved through the users' smart meter data, and users are aggregated into K categories. The results of optimal K category prediction under the family behavior model are summarized as the final prediction outcome. This idea framework is tested on real users' smart meter data, and its performance is comprehensively compared with different benchmarks. The results present strong compatibility in the small-scale users load forecasting model at various periods of the day and swift short-term prediction of users load compared to other prediction models. The time is shortened by 1/4 compared with the GRU/LSTM model. Furthermore, the accuracy is improved to 92.06% (MAPE is 7.94%). [ABSTRACT FROM AUTHOR]

The accuracy of short-term load forecasting plays an important role in the operation of the power system. However, because of the randomness of load data, it is a difficult task to provide accurate load forecasting. In this work, a short-term load forecasting approach integrating empirical mode decomposition (EMD), bidirectional long short-term memory (BiLSTM) and attention mechanism is proposed. At first, the electric load series are decomposed into several intrinsic mode functions (IMFs) by EMD. Then a BiLSTM neural network based on attention mechanism is applied on each of the extracted IMFs to predict the tendencies of these IMFs. At last, the prediction results of all IMFs are combined to get the final prediction result of electric load. The proposed approach is evaluated on a real-world dataset from Australian Energy Market Operator. The experimental results demonstrates that the prediction accuracy of the proposed approach can be greatly improved, compared with the other 7 benchmark models. The experiments also showed that the recommended number of IMFs are either 3 or 4 based on both prediction accuracy and running time. [ABSTRACT FROM AUTHOR]

The accurate short-term load forecasting can pave the way for improving, planning and maintenance of electric power systems. In this work, a novel Bayesian deep learning framework has been developed on BiLSTM + dropout network for analyzing short-term load prediction. The proposed framework improves the prediction accuracy by learning the uncertainties as well as reducing the data overfitting. Furthermore, a hierarchical clustering technique is applied to group consumers of similar behaviors in utilizing the power to improve the accuracy of load forecasting. The proposed framework is implemented using the MATLAB platform and tested on CER smart meter data. The RMSE, MAE and MAPE benchmark parameters are considered for comparing the proposed framework with the existing state-of-the-art techniques, viz., LSTM dropout, GRU, SVR and ARIMA. From the experimental results, it is evident that the proposed framework has achieved a better prediction accuracy despite the dataset having different load profiles, huge number of customers, uncertainties and volatility. [ABSTRACT FROM AUTHOR]

Accurate electricity load forecasting is critical to power system operation. Prediction error of load forecasting can be greatly reduced by utilizing knowledge transferred from other related tasks. To further improve the effectiveness of transfer, knowledge can be transferred from multiple sources to increase the chance of finding samples closely related to the target. In this work, a multi-source instances transfer algorithm based on domain-to-domain similarity and sample to domain similarity is developed and a bagging-based re-sampling transfer regression framework is constructed. Experimental evaluation on a real-world dataset shows that forecasting performance can be significantly improved by transferring useful data from more sources. Negative transfer is avoided effectively. [ABSTRACT FROM AUTHOR]