Interval Load Forecasting for Individual Households in the Presence of Electric Vehicle Charging

The transition to Electric Vehicles (EV) in place of traditional internal combustion engines is increasing societal demand for electricity. The ability to integrate the additional demand from EV charging into forecasting electricity demand is critical for maintaining the reliability of electricity generation and distribution. Load forecasting studies typically exclude households with home EV charging, focusing on offices, schools, and public charging stations. Moreover, they provide point forecasts which do not offer information about prediction uncertainty. Consequently, this paper proposes the Long Short-Term Memory Bayesian Neural Networks (LSTM-BNNs) for household load forecasting in presence of EV charging. The approach takes advantage of the LSTM model to capture the time dependencies and uses the dropout layer with Bayesian inference to generate prediction intervals. Results show that the proposed LSTM-BNNs achieve accuracy similar to point forecasts with the advantage of prediction intervals. Moreover, the impact of lockdowns related to the COVID-19 pandemic on the load forecasting model is examined, and the analysis shows that there is no major change in the model performance as, for the considered households, the randomness of the EV charging outweighs the change due to pandemic.

Gaussian Process-aided Transfer Learning for Probabilistic Load Forecasting against Anomalous Events

A probabilistic load forecasting method that can deal with sudden load pattern changes caused by abnormal events such as COVID-19 is proposed in this paper. The deep residual network (ResNet) is first applied to extract the load pattern for the normal period from historical data. When an abnormal event occurs, a Gaussian Process (GP) with a composite kernel is utilized to adapt to the changes on load pattern by estimating the forecasting residual of the ResNet. The designed kernel enables the proposed method to adapt rapidly to changes in the load pattern and effectively quantify the uncertainties caused by the abnormal event using a few training samples. Comparative tests with state-of-the-art point and probabilistic forecasting methods demonstrate the effectiveness of the proposed method. IEEE

Residential Load Forecasting based on Deep Neural Network

This paper presents residential load forecasting using multivariate multi-step Deep Neural Networks (DNN) such as LSTM, CNN, Stacked LSTM, and Hybrid CNN-LSTM. A preliminary Exploratory Data Analysis (EDA) is conducted, and the decision variables are identified. An elbowing method is used to determine the number of clusters. Data is categorized based on weekdays, weekends, vacations, and Covid-Lockdown. Dimensionality-reduction using principal component analysis (PCA) is conducted. Seasonality-based clustering is found to improve the DNN model prediction accuracy further. A comparative analysis employs error metrics such as RMSE, MSE, MAPE, and MAE. The multivariate LSTM model with feedback is found to be the best fit model with the better performance indices. © 2023 IEEE.

A Hybrid Deep Neural Network Architecture for Day-Ahead Electricity Forecasting: Post-COVID Paradigm

Predicting energy demand in adverse scenarios, such as the COVID-19 pandemic, is critical to ensure the supply of electricity and the operation of essential services in metropolitan regions. In this paper, we propose a deep learning model to predict the demand for the next day using the "IEEE DataPort Competition Day-Ahead Electricity Demand Forecasting: Post-COVID Paradigm” database. The best model uses hybrid deep neural network architecture (convolutional network–recurrent network) to extract spatial-temporal features from the input data. A preliminary analysis of the input data was performed, excluding anomalous variables. A sliding window was applied for importing the data into the network input. The input data was normalized, using a higher weight for the demand variable. The proposed model's performance was better than the models that stood out in the competition, with a mean absolute error of 2361.84 kW. The high similarity between the actual demand curve and the predicted demand curve evidences the efficiency of the application of deep networks compared with the classical methods applied by other authors. In the pandemic scenario, the applied technique proved to be the best strategy to predict demand for the next day.

Data-Driven Resilient Load Forecasting Model for Smart Metered Distribution System

The change in the electricity demand pattern globally due to sudden extreme weather conditions or situations like COVID 19 pandemic has brought unanticipated challenges for the electric utilities and operators around the world. This work primarily deals with the issue of load forecasting during such type of high impact low frequency (HILF) events. In this paper, we propose a novel resilient short-term load forecasting model capable of producing good forecasting performance for normal as well as critical situations during the COVID 19 pandemic and will also be useful for load forecasting for other HILF situations like natural calamity effect on load demand of the power system. The proposed method uses a feed-forward neural network (FFNN) with an added training feature named resiliency factor to forecast load in both regular and special scenarios. The resiliency factor for any type of node in the distribution system is decided by the power utility using the historical data and declared in advance. The proposed model is tested using the smart metered data available from a real-life distribution grid of an academic cum residential campus. The model is giving satisfactory results for both normal as well as COVID scenario for the said network. © 2023 Taylor & Francis Group, LLC.

Diffusion Convolutional Recurrent Neural Network-Based Load Forecasting During COVID-19 Pandemic Situation

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, single-area, 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. © 2022 Lavoisier. All rights reserved.

Short-term load forecasting based on machine learning and epidemic association features

Accurate power load forecasting is an important guarantee for normal operation of a power system. There have been problems of large fluctuations in load demand and difficulty in modeling historical reference load during the COVID-19 outbreak. Thus this paper proposes a short-term load forecasting method based on machine learning, silent index and rolling anxiety index. First, Google mobility data and epidemic data are used to construct the silent index and rolling anxiety index to quantify the impact of the economic and epidemic developments on the power load. Then, the maximal information coefficient is used to analyze the strong correlation factors of power load during the epidemic and introduce epidemic load correlation characteristics. Finally, meteorological data, historical load and the constructed epidemic correlation features are combined as the input variables of the prediction model, and the prediction algorithm is analyzed by multiple machine learning models. The results show that the load forecasting model with the introduction of the epidemic correlation features can effectively improve the accuracy of load forecasting during the epidemic. © 2022 Power System Protection and Control Press. All rights reserved.

Smart short-term electric load forecasting considering the Covid-19 epidemic impact based on deep learning

Short-term load forecasting is essential for the power company's operation and grid operators because it is necessary to ensure adequate capacity and proper power generation arrangement;this will affect operating efficiency and short-term decisions. Meanwhile, the Covid-19 epidemic as a nonlinear factor will be effective in short-term load forecasting and based on previous solutions, electrical load forecasting may not be accurate. A nonlinear and complex relationship between the factors affecting the load forecasting problem explains the need to use intelligent methods such as machine learning. This paper analyses the effect of Covid-19 epidemic countermeasures on short-term electric load forecasting in Iran. To forecast the short term electrical load, a deep neural network with a hybrid architecture and peak power consumption data, average temperature, and Covid-19 epidemic countermeasure data over 15 months during the Covid-19 epidemic was used. The results indicate an increase in forecasting accuracy considering the countermeasure's data. Also, the proposed model validation with data related to the fourth wave of the Covid-19 epidemic and the data of countermeasures modeling in Iran show the effectiveness and reasonable accuracy of the proposed model during the Covid19 epidemic. © 2022 IEEE.

Smart Short-Term Load Forecasting through Coordination of LSTM-Based Models and Feature Engineering Methods during the COVID-19 Pandemic

Short-term load forecasting is essential for power companies because it is necessary to ensure sufficient capacity. This article proposes a smart load forecasting scheme to forecast the short-term load for an actual sample network in the presence of uncertainties such as weather and the COVID-19 epidemic. The studied electric load data with hourly resolution from the beginning of 2020 to the first seven days of 2021 for the New York Independent Operator is the basis for the modeling. The new components used in this article include the coordination of stacked long short-term memory-based models and feature engineering methods. Also, more accurate and realistic modeling of the problem has been implemented according to the existing conditions through COVID-19 epidemic data. The influential variables for short-term load forecasting through various feature engineering methods have contributed to the problem. The achievements of this research include increasing the accuracy and speed of short-term electric load forecasting, reducing the probability of overfitting during model training, and providing an analytical comparison between different feature engineering methods. Through an analytical comparison between different feature engineering methods, the findings of this article show an increase in the accuracy and speed of short-term load forecasting. The results indicate that combining the stacked long short-term memory model and feature engineering methods based on extra-trees and principal component analysis performs well. The RMSE index for day-ahead load forecasting in the best engineering method for the proposed stacked long short-term memory model is 0.1071. © 2023 Taylor & Francis Group, LLC.

Short-term load forecasting based on machine learning and epidemic association features

Accurate power load forecasting is an important guarantee for normal operation of a power system. There have been problems of large fluctuations in load demand and difficulty in modeling historical reference load during the COVID-19 outbreak. Thus this paper proposes a short-term load forecasting method based on machine learning, silent index and rolling anxiety index. First, Google mobility data and epidemic data are used to construct the silent index and rolling anxiety index to quantify the impact of the economic and epidemic developments on the power load. Then, the maximal information coefficient is used to analyze the strong correlation factors of power load during the epidemic and introduce epidemic load correlation characteristics. Finally, meteorological data, historical load and the constructed epidemic correlation features are combined as the input variables of the prediction model, and the prediction algorithm is analyzed by multiple machine learning models. The results show that the load forecasting model with the introduction of the epidemic correlation features can effectively improve the accuracy of load forecasting during the epidemic. © 2022 Power System Protection and Control Press. All rights reserved.

General short-term load forecasting based on multi-task temporal convolutional network in COVID-19

The spread of the global COVID-19 epidemic has resulted in significant shifts in electricity consumption compared to regular days. It is unknown if standard single-task, single-indicator load forecasting algorithms can accurately reflect COVID-19 load patterns. Power practitioners urgently want a simple, efficient, and accurate solution for anticipating reliable load. In this paper, we first propose a unique collaborative TCN-LSTM-MTL short-term load forecasting model based on mobility data, temporal convolutional networks, and multi-task learning. The addition of the parameter sharing layers and the structure with residual convolution improves the data input diversity of the forecasting model and enables the model to obtain a wider time series receptive field. Then, to demonstrate the usefulness of the mobility optimized TCN-LSTM-MTL, tests were conducted in three levels and twelve base regions using 19 different benchmark models. It is capable of controlling predicting mistakes to within 1 % in the majority of tasks. Finally, to rigorously explain the model, the Shapley additive explanations (SHAP) visual model interpretation technology based on game theory is introduced. It examines the TCN-LSTM-MTL model's internal mechanism at various time periods and establishes the validity of the mobility indicators as well as the asynchronous relationship between indicator significance and real contribution.

Short-Term State Electricity Load Forecasting Based on Transfer-Informer

The worldwide COVID-19 pandemic has caused an enormous impact on the operation mode of human society. Such sudden events bring sharp fluctuations and data inadequacy in datasets of several areas, which leads to challenges in solving related problems. Traditional deep learning models like CNN have shown relatively poor performance with small datasets during the COVID-19 pandemic. This is because the data insufficiency and fluctuations lead to serious problems in the training process. In our work, an Informer framework combined with Transfer learning methods (Transfer-Informer) is proposed to solve the data insufficiency in emergency situations, as well as to provide a more efficient self-attention mechanism for deep feature mining, with two distinctive advantages: (1) The ProbSpares self-attention mechanisms, which enables the proposed model to highlight dominant information and extract more typical features from time-series datasets. (2) The Transfer learning framework improves the generalization capability of the model, by transferring basic knowledge from normal situations to emergency cases with fewer data. In our experiments, Transfer-Informer is applied to short-term load forecasting, which achieves better predicting accuracy than traditional models. The empirical results indicate that the proposed model has put forward a baseline for short-term load forecasting in emergency situations and provided a feasible method to tackle sudden fluctuations in real problem-solving. © 2022 IEEE.

Short-Term State Electricity Load Forecasting Based on Transfer-Informer

The worldwide COVID-19 pandemic has caused an enormous impact on the operation mode of human society. Such sudden events bring sharp fluctuations and data inadequacy in datasets of several areas, which leads to challenges in solving related problems. Traditional deep learning models like CNN have shown relatively poor performance with small datasets during the COVID-19 pandemic. This is because the data insufficiency and fluctuations lead to serious problems in the training process. In our work, an Informer framework combined with Transfer learning methods (Transfer-Informer) is proposed to solve the data insufficiency in emergency situations, as well as to provide a more efficient self-attention mechanism for deep feature mining, with two distinctive advantages: (1) The ProbSpares self-attention mechanisms, which enables the proposed model to highlight dominant information and extract more typical features from time-series datasets. (2) The Transfer learning framework improves the generalization capability of the model, by transferring basic knowledge from normal situations to emergency cases with fewer data. In our experiments, Transfer-Informer is applied to short-term load forecasting, which achieves better predicting accuracy than traditional models. The empirical results indicate that the proposed model has put forward a baseline for short-term load forecasting in emergency situations and provided a feasible method to tackle sudden fluctuations in real problem-solving. © 2022 IEEE.

Smart Short-Term Load Forecasting through Coordination of LSTM-Based Models and Feature Engineering Methods during the COVID-19 Pandemic

Short-term load forecasting is essential for power companies because it is necessary to ensure sufficient capacity. This article proposes a smart load forecasting scheme to forecast the short-term load for an actual sample network in the presence of uncertainties such as weather and the COVID-19 epidemic. The studied electric load data with hourly resolution from the beginning of 2020 to the first seven days of 2021 for the New York Independent Operator is the basis for the modeling. The new components used in this article include the coordination of stacked long short-term memory-based models and feature engineering methods. Also, more accurate and realistic modeling of the problem has been implemented according to the existing conditions through COVID-19 epidemic data. The influential variables for short-term load forecasting through various feature engineering methods have contributed to the problem. The achievements of this research include increasing the accuracy and speed of short-term electric load forecasting, reducing the probability of overfitting during model training, and providing an analytical comparison between different feature engineering methods. Through an analytical comparison between different feature engineering methods, the findings of this article show an increase in the accuracy and speed of short-term load forecasting. The results indicate that combining the stacked long short-term memory model and feature engineering methods based on extra-trees and principal component analysis performs well. The RMSE index for day-ahead load forecasting in the best engineering method for the proposed stacked long short-term memory model is 0.1071. [ FROM AUTHOR]

A novel deep learning framework with a COVID-19 adjustment for electricity demand forecasting

Electricity demand forecasting is crucial for practical power system management. However, during the COVID-19 pandemic, the electricity demand system deviated from normal system, which has detrimental bias effect in future forecasts. To overcome this problem, we propose a deep learning framework with a COVID-19 adjustment for electricity demand forecasting. More specifically, we first designed COVID-19 related variables and applied a multiple linear regression model. After eliminating the impact of COVID-19, we employed an efficient deep learning algorithm, long short-term memory multiseasonal net deseasonalized approach, to model residuals from the linear model aforementioned. Finally, we demonstrated the merits of the proposed framework using the electricity demand in Taixing, Jiangsu, China, from May 13, 2018 to August 2, 2021. © 2023 The Author(s)

General Short-Term Load Forecasting Based on Multi-Task Temporal Convolutional Network in COVID-19

The spread of the global COVID-19 epidemic has resulted in significant shifts in electricity consumption compared to regular days. It is unknown if standard single-task, single-indicator load forecasting algorithms can accurately reflect COVID-19 load patterns. Power practitioners urgently want a simple, efficient, and accurate solution for anticipating reliable load. In this paper, we first propose a unique collaborative TCN-LSTM-MTL short-term load forecasting model based on mobility data, temporal convolutional networks, and multi-task learning. The addition of the parameter sharing layers and the structure with residual convolution improves the data input diversity of the forecasting model and enables the model to obtain a wider time series receptive field. Then, to demonstrate the usefulness of the mobility optimized TCN-LSTM-MTL, tests were conducted in three levels and twelve base regions using 19 different benchmark models. It is capable of controlling predicting mistakes to within 1% in the majority of tasks. Finally, to rigorously explain the model, the Shapley additive explanations (SHAP) visual model interpretation technology based on game theory is introduced. It examines the TCN-LSTM-MTL model's internal mechanism at various time periods and establishes the validity of the mobility indicators as well as the asynchronous relationship between indicator significance and real contribution.

In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance

In power grids, short-term load forecasting (STLF) is crucial as it contributes to the optimization of their reliability, emissions, and costs, while it enables the participation of energy companies in the energy market. STLF is a challenging task, due to the complex demand of active and reactive power from multiple types of electrical loads and their dependence on numerous exogenous variables. Amongst them, special circumstances-such as the COVID-19 pandemic-can often be the reason behind distribution shifts of load series. This work conducts a comparative study of Deep Learning (DL) architectures-namely Neural Basis Expansion Analysis Time Series Forecasting (N-BEATS), Long Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN)-with respect to forecasting accuracy and training sustainability, meanwhile examining their out-of-distribution generalization capabilities during the COVID-19 pandemic era. A Pattern Sequence Forecasting (PSF) model is used as baseline. The case study focuses on day-ahead forecasts for the Portuguese nationa115-minute resolution net load time series. The results can be leveraged by energy companies and network operators (i) to reinforce their forecasting toolkit with state-of-the-art DL models;(ii) to become aware of the serious consequences of crisis events on model performance;(iii) as a high-level model evaluation, deployment, and sustainability guide within a smart grid context. © 2022 IEEE.

Pandemic-Aware Electric Load Forecasting: A Multitask Bidirectional LSTM/CNN Model

COVID-19 pandemic has brought major uncertainty in load forecasting. Enforcing and relaxing lockdown rules, infection numbers, and the changing habits of people are the main causes of this uncertainty. Electric load forecasting maintains the balance between electric supply and demand. It also assists electric utilities in pricing their services, planning, and managing their infrastructure. This paper proposes two pandemic-aware load forecasting models (i) a city-level model, applied on the cities of Ottawa and Toronto, predicting hourly load using weather and pandemic-related features including population mobility and the number of daily COVID-19 infections, and (ii) a second open-source model forecasting quarter-hourly residential-level loads using weather and population mobility features for the city of Pune in India. Both models utilize multitask learning to jointly learn and predict future electric loads. The quarter-hourly model uses Bi-directional Long Short-Term Memory (LSTM) to learn from COVID's specific features, and a Convolutional Neural Network (CNN) to learn from the historical load data before the pandemic. The multitask nature of the model allows for incorporating multiple datasets with different numbers of features. The residential-level multitask model allowed for learning from long-term data before COVID-19 using weather features, short-term load data, and the mobility data. Multitask learning has also enabled the use of two datasets with different numbers of features due to the lack of mobility data pre-COVID. © 2022 IEEE.

Short-Term Load Forecasting Using a Parallel CNN-BPNN Prediction Model with COVID-19 Pandemic Restriction as an Added Input Parameter and ReLU Activation Function

Short-term load forecasting provides a vital tool for the power system. This study delved into applying a hybridized machine learning algorithm to improve load forecasting accuracy. It aims to investigate the accuracy of the parallel CNN-BPNN prediction model in short-term load forecasting with Philippine pandemic restriction as an added parameter and a ReLU activation function. The CNN, BPNN, and the proposed parallel CNN-BPNN models were implemented using Python. They were trained, validated, and tested using the input parameters such as historical power demand, day of weeks/ Holidays, meteorological data such as temperature, wind speed, humidity, and COVID-19 pandemic restriction. The accuracy of the three models was tested using the MAPE. Results showed that the proposed model achieved the lowest MAPE of 3.52 %, lower than that of the CNN, 4.62%, and BPNN, 3.98%. Furthermore, Pearson correlation analysis showed that the relationship between electricity usage and mobility constraints is moderately correlated with a correlation value of -0.57. © 2022 WCSE. All Rights Reserved.

A novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization for short-term load forecasting during the COVID-19 pandemic

The coronavirus disease 2019 pandemic has significantly impacted the world. The sudden decline in electricity load demand caused by strict social distancing restrictions has made it difficult for traditional models to forecast the load demand during the pandemic. Therefore, in this study, a novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization is proposed for short-term load forecasting during the pandemic. First, a knowledge base containing mobility data is constructed, which can reflect the changes in visitor volume in different regions and buildings based on mobile services. Therefore, the sudden decline in load can be analyzed according to the socioeconomic behavior changes during the pandemic. Furthermore, a new transfer deep learning model is proposed to address the problem of limited mobility data associated with the pandemic. Moreover, reinforcement learning is employed to optimize the hyperparameters of the proposed model automatically, which avoids the manual adjustment of the hyperparameters, thereby maximizing the forecasting accuracy. To enhance the hyperparameter optimization efficiency of the reinforcement-learning agents, a new advance forecasting method is proposed to forecast the state-action values of the state space that have not been traversed. The experimental results on 12 real-world datasets covering different countries and cities demonstrate that the proposed model achieves high forecasting accuracy during the coronavirus disease 2019 pandemic. © 2022 - IOS Press. All rights reserved.