Electricity Load Data Research Articles

An optimized method for short-term load forecasting based on feature fusion and ConvLSTM-3D neural network

As renewable energy continues to penetrate modern power systems, accurate short-term load forecasting is crucial for optimizing power generation resource allocation and reducing operational costs. Traditional forecasting methods often overlook key factors such as holiday load variations and differences in user electricity consumption behavior, resulting in reduced accuracy. To address this, we propose an optimized short-term load forecasting method based on time and weather-fused features using a ConvLSTM-3D neural network. The Prophet algorithm is first employed to decompose historical electricity load data, extracting feature components related to time variables. Simultaneously, the SHAP algorithm filters weather variables to identify highly correlated weather features. A time attention mechanism is then applied to fuse these features based on their correlation weights, enhancing their impact within the time series. Finally, the ConvLSTM-3D model is trained on the fused features to generate short-term load forecasts. A case study using real-world data validates the proposed method, demonstrating significant improvements in forecasting accuracy.

Development of an Optimized Neural Network Model using Hyperparameters Optimization for Electrical Load Prediction

Electrical load prediction has become essential to the efficient operation, control and management of modern electric power systems. Various machine learning prediction models have been developed for electrical load prediction, this includes Support Vector Regression, Fuzzy Logic and Neural Network (NN) modelling approaches. However, incorrect selection of model hyperparameters, which are parameters that affect the output of the prediction models, could result in low prediction accuracy of machine learning models. Hence, the development of an optimized NN model for electrical load prediction was presented in this study. Historical daily data of temperature, rainfall, relative humidity and windspeed for Osogbo, Nigeria was obtained from the National Aeronautics and Space Administration website; while electrical load data for the same location was collected from the Transmission Company of Nigeria. The data captured a period of five years (2017 to 2021). The NN models were developed with MATLAB R2022a software, and two hyperparameters, hidden layers and neuron counts, were optimized using the Bayesian optimization technique to enhance the quality of the models. The models were evaluated using mean absolute error (MAE), and root mean square error (RMSE). The MAE and RMSE for the non-optimized NN model were 6.5247 and 8.2725 respectively. Meanwhile, for the optimized NN model, the MAE and RMSE were 5.6571 and 7.4289 respectively. The obtained results show that the optimized NN performed better than the non-optimized NN models. Therefore, for more accurate load prediction, the method developed of this research is suggested for use by utility providers.

A multi-year campus-level smart meter database

With the growing need for precise campus electricity management, understanding load patterns is crucial for improving energy efficiency and optimizing energy use. However, detailed electricity load data for campus buildings and their internal equipment is often lacking, hindering research. This paper introduces an energy consumption monitoring dataset from The Hong Kong University of Science and Technology (HKUST) campus in Hong Kong, comprising data from over 1400 meters across more than 20 buildings and collected over two and a half years. Using the Brick Schema curation strategy, raw data was curated into a research-ready format. This dataset supports various research tasks, including load pattern recognition, fault detection, demand response strategies, and load forecasting.

IoT-driven load forecasting with machine learning for logistics planning

Forecasting electricity load in logistics is crucial for managing dynamic energy demands. This research introduces the Integrated Load Forecasting System (ILFS), integrating IoT-driven load forecasting with advanced machine learning. As pioneers in logistics-focused electricity load forecasting, we acknowledge challenges posed by operational metrics, external factors, and diverse features. Starting with thorough preparation, including managing missing data and normalization, ILFS incorporates novel approaches such as Hybrid Boruta with XGBoost (BXG) for feature selection and Uniform Manifold Projection and Approximation (UMAP) for lower dimensionality. In the classification phase, we introduce a pioneering approach: the Hybrid Huber Regression with ResNet (HRRN) model, fine-tuned using the Coyote Optimization Algorithm (COA). Demonstrating scalability and interpretability, ILFS adjusts to various electricity load data scenarios, capturing trends in logistics supply warehouses across different days. Validation metrics underscore ILFS’s efficacy, achieving 98% accuracy, 4 MAE, 12 MSE, 5 RMSE, and 0.99 R-squared (R2). With an average execution time of 7.2 s, ILFS outperforms current techniques, and rigorous statistical analyses support this superiority. ILFS emerges as a pivotal solution, meeting the necessities of precise electricity load forecasting in logistics driven by IoT technologies. This research strides towards harmonious integration of load forecasting, IoT, and logistics planning, ushering in advancements in the field.

Time Series Analysis in Electrical Load Forecasting

Time series analysis in electricity load projection is a key part of the energy sector because it makes it possible to control and distribute energy more efficiently. It is important to have accurate load forecasts in order to balance supply and demand, make power systems run more efficiently, and lower operating costs. This essay covers a wide range of ways that time series analysis can be used to guess how much electricity will be used. The study looks at a number of different models, such as the autoregressive integrated moving average (ARIMA), exponential smoothing, and machine learning methods like Long Short-Term Memory (LSTM) networks. These models are judged by how well they can show the patterns and time relationships that are common in electricity load data. A lot of attention is paid to the problems that come up because of non-stationarity, timing, and outside factors like weather that cause load changes. The study talks about how feature selection, data pre-processing, and model evaluation can help make forecasts more accurate. The study shows the trade-offs between model interpretability and forecasting power by comparing how well standard statistical methods and new machine learning techniques work. The study also talks about how mixed models, which take the best parts of more than one method and combine them, might help make forecasts more accurate. The results make it clear how important time series analysis is for building accurate load predicting models, which are needed to keep modern power systems reliable and efficient.

Robust load feature extraction based secondary VMD novel short-term load demand forecasting framework

Load forecasting, as a crucial component of the electricity market, plays a significant role in ensuring the secure operation and rational planning of the power grid. However, as the power system becomes increasingly intricate, the demands on load forecasting techniques have escalated. Consequently, to mitigate the errors in short-term load forecasting (STLF) caused by uncertainty factors and to accommodate daily forecasting under abnormal electricity load conditions, this paper proposes a hybrid load forecasting model that combines an improved Secondary Variational Mode Decomposition (SVMD) algorithm with the Informer model. Employing electricity load data from the Panama context, the data is divided into four distinct experimental cases. The outcomes manifest that in contrast to the baseline model, the proposed approach engenders a minimal reduction of 15.08%, 12.95%, and 13.21% in Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE), respectively. Furthermore, supplementary experimental results demonstrate that the model exhibits strong robustness.

A Short term Electricity Load Forecasting for Community Residents Based on Federated Learning and Considering Privacy Protection

INTRODUCTION: As the penetration rate of renewable energy increases and patterns of energy demand evolve, fluctuations on both the supply and demand sides of electricity are becoming more pronounced. Consequently, accurate forecasting of community residential electrical loads has become crucial. OBJECTIVES: Although the widespread adoption of smart meters among residents provides abundant data for model training, strict challenges arise during the training process due to the need for privacy protection and data security. METHODS: This paper proposes a privacy-preserving community residential short-term electric load forecasting method based on federated learning. Initially, the method applies shared random masking encryption to the sensitive data of community residents, ensuring data privacy while maintaining consistency with the original data after preprocessing. Subsequently, a private data aggregation scheme is established to perform dynamic clustering of the community’s electrical load. RESULTS: The clustered model then serves as the basis for establishing individual load forecasting models for each category of community residents to predict short-term electrical loads. Finally, an empirical analysis is performed using the electrical load data from 120 households across 6 communities in a city in Southern China. CONCLUSION: The analysis demonstrates that the proposed method can achieve the prediction of community residential electrical loads without sharing residents’ data, thus verifying the effectiveness of this approach.

Electric load forecasting under false data injection attacks via denoising deep learning and generative adversarial networks

AbstractAccurate 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.

Non-Intrusive Load Monitoring Based on Dimensionality Reduction and Adapted Spatial Clustering

Non-invasive load monitoring (NILM) deduces changes in energy consumption patterns and operational statuses of electrical equipment from power signals in the feed line. With the emergence of fine-grained power load distribution, the importance of utilizing this technology for implementing demand-side energy management in smart grid development has become increasingly prominent. To address the issue of low load identification accuracy stemming from complex and diverse load types, this paper introduces a NILM method based on uniform manifold approximation and projection (UMAP) reduction and enhanced density-based spatial clustering of applications with noise (DBSCAN). Firstly, this paper combines the characteristics of user load under transient and steady-state conditions and selects data with significant differences to construct a load-characteristic database. Additionally, UMAP is employed to reduce the dimensionality of high-dimensional load features and rebuild a load feature database. Subsequently, DBSCAN is utilized to categorize typical user loads, followed by a correlation analysis with the load-characteristic database to determine the types or classes of loads that involve switching actions. Finally, this paper simulates and analyzes the proposed method using the electricity consumption data of industrial users from the CER–Electricity–Data dataset. It identifies the electricity load data commonly utilized by users in a specific area of Zhejiang Province in China. The experimental results indicate that the accuracy of the proposed non-invasive load identification method reaches 95%. Compared to the wavelet transform, decision tree, and backpropagation network methods, the improvement is approximately 5%.

Short-Term Power Load Forecasting Based on Secondary Cleaning and CNN-BILSTM-Attention

Accurate power load forecasting can provide crucial insights for power system scheduling and energy planning. In this paper, to address the problem of low accuracy of power load prediction, we propose a method that combines secondary data cleaning and adaptive variational mode decomposition (VMD), convolutional neural networks (CNN), bi-directional long short-term memory (BILSTM), and adding attention mechanism (AM). The Inner Mongolia electricity load data were first cleaned use the K-means algorithm, and then further refined with the density-based spatial clustering of applications with the noise (DBSCAN) algorithm. Subsequently, the parameters of the VMD algorithm were optimized using a multi-strategy Cubic-T dung beetle optimization algorithm (CTDBO), after which the VMD algorithm was employed to decompose the twice-cleaned load sequences into a number of intrinsic mode functions (IMFs) with different frequencies. These IMFs were then used as inputs to the CNN-BILSTM-Attention model. In this model, a CNN is used for feature extraction, BILSTM for extracting information from the load sequence, and AM for assigning different weights to different features to optimize the prediction results. It is proved experimentally that the model proposed in this paper achieves the highest prediction accuracy and robustness compared to other models and exhibits high stability across different time periods.

Study on the burial depth calculation method for AC submarine cable based on the surface optical fiber monitoring temperature

AbstractThe partial exposure of submarine cable may cause damage to the metal sheath, which will affect its safe and stable operation. Existing detection methods for burial depth of submarine cables are difficult to implement and have a long detection period. In this contribution, a method is proposed to calculate the burial depth of alternating current (AC) submarine cable based on surface optical fiber monitoring temperature. According to the functional relationship between the transient temperature rise of submarine cable outer sheath above the ambient temperature and the burial depth (in the IEC‐60853 standard), the burial depth of submarine cables is calculated. The optical fiber temperature, electric load and meteorological temperature data are used for 30 consecutive days in September 2020 to calculate the change of burial depth of AC 500 kV oil‐filled submarine cable. The calculation results are basically consistent with the detection conclusion of side‐scan sonar, which shows that the method can accurately calculate the burial depth of submarine cables and locate the exposed position. This provides a theoretical basis for the intelligent operation and maintenance of AC submarine cables.

Techno-economic analysis and dynamic power simulation of a hybrid solar-wind-battery system for power supply in rural areas in Pakistan

This study presents the optimal design and operation of a proposed hybrid renewable energy system (HRES) for the electrification of a residential building in rural areas in Pakistan. The main contributions of this study are twofold. Firstly, it develops a size optimization model based on the particle swarm optimization (PSO) technique to determine the optimal configuration for two hybrid renewable energy systems (HRES), including both grid-tied and off-grid modes, integrating wind and photovoltaic (PV) systems with battery storage. The optimal configuration is determined by minimizing the levelized cost of electricity, using local meteorological and electricity load data, along with technical specifications of the main HRES components. Secondly, dynamic simulations of two HRES configurations are conducted, using MATLAB Simulink, ensuring the optimal energy balance between multiple energy sources and the load at each operation hour. To meet an annual electrical demand of 131.035 MWh, the grid-tied HRES yields 146.081 MWh annually, with solar contributing 68.85 MWh and wind 77.272 MWh. Conversely, the off-grid system generates 133.533 MWh annually, with solar and wind output power at 43.932 MWh and 89.601 MWh, respectively. The grid-tied system achieves an LCOE of approximately 0.29 $/kWh, with optimal wind turbine and PV capacities of 11 kW and 29 kW, respectively. While in off-grid configuration, the off-grid scenario exhibits an LCOE of 0.91 $/kWh, with optimal capacities of 10 kW for wind turbine, 20 kW for PV, and 2437.5 AH for batteries. The findings provide insights relevant to diverse locations, emphasizing the importance of local meteorological and geographical data. Multiple case studies ensure the robustness and applicability of the proposed system under varying conditions.

A hybrid long-term industrial electrical load forecasting model using optimized ANFIS with gene expression programming

Electric energy demand forecasting is vital in contemporary power systems, especially amidst market deregulation trends and the increasing influence of industrial customers on power dynamics. However, existing forecasting models encounter challenges such as slow convergence and high complexity. Addressing these issues, this study proposes a hybrid forecasting model that combines the Adaptive Neuro-Fuzzy Inference System (ANFIS) with Gene Expression Programming (GEP) to enhance predictions of electrical energy consumption. Validated using real-time monthly electrical load data from an industrial user in Uganda, the hybrid model outperforms individual ANFIS and GEP models, demonstrating reduced errors and minimal computation time. The application of this hybrid model presents promising results, showcasing exceptional predictive capabilities and offering potential improvements in efficiency and precision for electrical energy consumption forecasting amidst market deregulation and evolving industrial dynamics.

Research on Electricity Load Forecasting Based on LSTM Networks and BP Networks

The aim of this study is to compare the performance of Long Short-Term Memory (LSTM) network with Back Propagation Neural Network (BP network) for electricity load forecasting. Two prediction methods are used in the study: the first one uses a sliding window approach to predict the load of the next hour using the electricity load data of the past 24 hours and external factors such as temperature and humidity; the second one uses the data of the same time point of the past 24 days to predict the load of the corresponding time point of the next day. The results show that in the first method, the BP network outperforms the LSTM in prediction; while in the second method, both networks perform poorly, but the LSTM network outperforms the BP network in prediction. This finding provides new insights into power load forecasting, which is important for power system efficiency and reliability improvement.

Deriving Input Variables through Applied Machine Learning for Short-Term Electric Load Forecasting in Eskilstuna, Sweden

As the demand for electricity, electrification, and renewable energy rises, accurate forecasting and flexible energy management become imperative. Distribution network operators face capacity limits set by regional grids, risking economic penalties if exceeded. This study examined data-driven approaches of load forecasting to address these challenges on a city scale through a use case study of Eskilstuna, Sweden. Multiple Linear Regression was used to model electric load data, identifying key calendar and meteorological variables through a rolling origin validation process, using three years of historical data. Despite its low cost, Multiple Linear Regression outperforms the more expensive non-linear Light Gradient Boosting Machine, and both outperform the “weekly Naïve” benchmark with a relative Root Mean Square Errors of 32–34% and 39–40%, respectively. Best-practice hyperparameter settings were derived, and they emphasize frequent re-training, maximizing the training data size, and setting a lag size larger than or equal to the forecast horizon for improved accuracy. Combining both models into an ensemble could the enhance accuracy. This paper demonstrates that robust load forecasts can be achieved by leveraging domain knowledge and statistical analysis, utilizing readily available machine learning libraries. The methodology for achieving this is presented within the paper. These models have the potential for economic optimization and load-shifting strategies, offering valuable insights into sustainable energy management.

Residential net load interval prediction based on stacking ensemble learning

In response to the high uncertainty associated with residential net load due to the coupling of distributed photovoltaic generation and user demand, this paper proposed a novel cluster-based stacking ensemble learning model for net load interval prediction. Firstly, the k-means algorithm is employed to discover the similarity in user electricity consumption patterns. Then, a RIME optimization algorithm with local enhancement (LRIME) is developed to optimize the parameters and weights of the base learners in stacking ensemble learning. Subsequently, base learners with strong predictive capabilities and significant diversity are chosen as the first-layer predictive models, extreme learning machine (ELM) is utilized as the second-layer predictive model, ultimately resulting in the proposed stacking ensemble learning prediction model. And utilizing the bootstrap method to fit the volatility of point predictions, different prediction intervals are obtained at varying confidence levels, aiming to quantify the integrated uncertainty in photovoltaic generation and load. Testing on the open Ausgrid electricity load data in Australia provided robust validation of the proposed method's effectiveness. In comparison with other outstanding prediction models, the proposed ensemble model can effectively capture the uncertainty in integrating photovoltaic generation and user load.

Resilient Electricity Load Forecasting Network with Collective Intelligence Predictor for Smart Cities

Accurate electricity forecasting is essential for smart cities to maintain grid stability by allocating resources in advance, ensuring better integration with renewable energies, and lowering operation costs. However, most forecasting models that use machine learning cannot handle the missing values and possess a single point of failure. With rapid technological advancement, smart cities are becoming lucrative targets for cyberattacks to induce packet loss or take down servers offline via distributed denial-of-service attacks, disrupting the forecasting system and inducing missing values in the electricity load data. This paper proposes a collective intelligence predictor, which uses modular three-level forecasting networks to decentralize and strengthen against missing values. Compared to the existing forecasting models, it achieves a coefficient of determination score of 0.98831 with no missing values using the base model in the Level 0 network. As the missing values in the forecasted zone rise to 90% and a single-model forecasting method is no longer effective, it achieves a score of 0.89345 with a meta-model in the Level 1 network to aggregate the results from the base models in Level 0. Finally, as missing values reach 100%, it achieves a score of 0.81445 by reconstructing the forecast from other zones using the meta-model in the Level 2 network.

A new Frontier in electric load forecasting: The LSV/MOPA model optimized by modified orca predation algorithm

Electric load forecasting is a vital task for energy management and policy-making. However, it is also a challenging problem due to the complex and dynamic nature of electric load data. In this paper, a novel technique, called LSV/MOPA, has been proposed for electric load forecasting. The technique is a hybrid model that combines the advantages of Long Short-Term Memory (LSTM) and Support Vector Regression (SVR), two powerful artificial intelligence algorithms. The hybrid model is further optimized by a newly Modified Orca Predation Algorithm (MOPA), which enhances the forecasting accuracy and efficiency. The LSV/MOPA model has been applied to historical electric load data from South Korea, covering four regions and 20 years. The LSV/MOPA model has been compared with other state-of-the-art forecasting techniques, including SVR/FFA, LSTM/BO, LSTM-SVR, and CNN-LSTM. The results show that the LSV/MOPA model with minimum average mean absolute percentage deviation error, including 365 in northern region, 12.8 in southern region, 8.6 in central region, and 30.8 in eastern region, provides the best fitting and outperforms the other techniques in terms of the Mean Absolute Percentage Deviation (MAPD) index, achieving lower values for all regions and years. The LSV/MOPA model also exhibits faster convergence and better generalization than the other techniques. This study demonstrates the effectiveness and superiority of the LSV/MOPA model for electric load forecasting and suggests its potential applications in other sectors where accurate forecasting is crucial.

Short-term power load forecasting using informer encoder and bi-directional LSTM

An innovative model called InE-BiLSTM is proposed here, which combines the Informer Encoder with a bidirectional LSTM (Bi-LSTM) network. The goal is to enhance the precision and efficacy of short-term electricity load forecasting. By integrating the long-term dependency capturing capability of the informer encoder with the advantages of Bi-LSTM in handling dynamic features in time series data, the InE-BiLSTM model effectively addresses complex patterns and fluctuations in electricity load data. The study begins by analyzing the current state of short-term electricity load forecasting, followed by a detailed introduction to the structure and principles of the InE-BiLSTM model. Results of the experiment demonstrate that, compared to the Informer, traditional Bi-LSTM, and Transformer models, the InE-BiLSTM model consistently outperforms them across various evaluation metrics.

Long Short-Term Memory-Based Twin Support Vector Regression for Probabilistic Load Forecasting.

A probabilistic load forecast that is accurate and reliable is crucial to not only the efficient operation of power systems but also to the efficient use of energy resources. In order to estimate the uncertainties in forecasting models and nonstationary electric load data, this study proposes a probabilistic load forecasting model, namely BFEEMD-LSTM-TWSVRSOA. This model consists of a data filtering method named fast ensemble empirical model decomposition (FEEMD) method, a twin support vector regression (TWSVR) whose features are extracted by deep learning-based long short-term memory (LSTM) networks, and parameters optimized by seeker optimization algorithms (SOAs). We compared the probabilistic forecasting performance of the BFEEMD-LSTM-TWSVRSOA and its point forecasting version with different machine learning and deep learning algorithms on Global Energy Forecasting Competition 2014 (GEFCom2014). The most representative month data of each season, totally four monthly data, collected from the one-year data in GEFCom2014, forming four datasets. Several bootstrap methods are compared in order to determine the best prediction intervals (PIs) for the proposed model. Various forecasting step sizes are also taken into consideration in order to obtain the best satisfactory point forecasting results. Experimental results on these four datasets indicate that the wild bootstrap method and 24-h step size are the best bootstrap method and forecasting step size for the proposed model. The proposed model achieves averaged 46%, 11%, 36%, and 44% better than suboptimal model on these four datasets with respect to point forecasting, and achieves averaged 53%, 48%, 46%, and 51% better than suboptimal model on these four datasets with respect to probabilistic forecasting.