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.

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 There have been problems of large fluctuations in load demand and difficulty in modeling historical reference load during the COVID-19 outbreak.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.

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]

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.

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.

Energy Management in an Agile Workspace using AI-driven Forecasting and Anomaly Detection

Smart building technologies transform buildings into agile, sustainable, and health-conscious ecosystems by leveraging IoT platforms. In this regard, we have developed a Persuasive Energy Conscious Network (PECN) at the University of Glasgow to understand the user-centric energy consumption patterns in an agile workspace. PECN consists of desk-level energy monitoring sensors that enable us to develop user-centric models that can be exploited to characterize the normal energy usage behavior of an office occupant. In this study, we make use of staked long short-term memory (LSTM) to forecast future energy demands. Moreover, we employed statistical techniques to automate the detection of anomalous power consumption patterns. Our experimental results indicate that post-anomaly resolution leads to 6.37% improvement in the forecasting accuracy. © 2022 IEEE.

Short-Term Load Forecasting Model Considering the Impact of COVID-19 Lockdown in Bangladesh

The impact of COVID-19 lockdown on short-term load forecasting in Bangladesh has been investigated in this paper. Machine learning models have been proved to be the most efficient regarding such prediction. Models like Artificial Neural Network (ANN), Long Short-Term Memory (LSTM) and Random Forest (RF) have been used in this study to build robust models taking the COVID-19 lockdown situation into account. Data sets for the models were formulated by taking daily generation reports, weather indicators and holidays. This study aims to compare different machine learning models to find out the best model for load forecasting keeping into account the impact of COVID-19 lockdown. The results of these methods have been compared based on accuracy metrics. It has been observed that LSTM shows the least error among the compared models. © 2021 IEEE.

Short-term power load forecasting during the COVID-19 pandemic using XGBoost and Copula theory

The global coronavirus disease (COVID-19) has brought great challenges to the power systems due to its limitations on social, economic and productive activities. This paper proposes a short-term load forecasting method during COVID-19 pandemic based on copula theory and eXtreme Gradient Boosting (XGBoost). In this method, the coupling relationship among the cross-domain meteorological, public health, and mobility time-series data are fully analyzed based on copula theory, which is used for the short-term power load forecasting based on multi-factor fusion XGBoost algorithm. The proposed method has been fully evaluated and benchmarked on available cross-domain open-access United States data to demonstrate its effectiveness and superiority on short-term load forecasting of COVID-19. © 2021 IEEE

An Ensemble Approach for Short-Term Load Forecasting for DISCOMS of Delhi Across the COVID-19 Scenario

The Covid-19 has presented unforeseen challenges to the world that has never been experienced before in history. None of the sectors remained unaffected witnessed various changes in their day-To-day operations. The impact has also been observed in the power sector, which can easily be illustrated with load fluctuations. The balancing of load supply in the energy sector is itself one of the critical complex tasks which becomes more vulnerable to deviation in case of these unforeseen events. Despite using advanced systems like machine learning artificial intelligence for load forecasting, utilities found the task challenging. This paper covers the impact of lockdown on load patterns of the Discoms of Delhi in the year 2020-21. The effect of weather on load is also analysed to demonstrate the critical correlation between them. The performance of the ensemble technique that has been proven beneficial for better load forecasting has outperformed other existing models, even in the current pandemic situation, has also been analysed validated through a comparative analysis against popular benchmark models. © 2021 IEEE.

Short-Term Power Load Forecasting Under COVID-19 Based on Graph Representation Learning With Heterogeneous Features

Since 2020, the COVID-19 has spread globally at an extremely rapid rate. The epidemic, vaccination, and quarantine policies have profoundly changed economic development and human activities worldwide. As many countries start to resume economic activities aiming at a "living with COVID " new normal, a short-term load forecasting technique incorporating the epidemic's effects is of great significance to both power system operation and a smooth transition. In this context, this paper proposes a novel short-term load forecasting method under COVID-19 based on graph representation learning with heterogeneous features. Unlike existing methods that fit power load data to time series, this study encodes heterogeneous features relevant to electricity consumption and epidemic status into a load graph so that not only the features at each time moment but also the inherent correlations between the features can be exploited;Then, a residual graph convolutional network (ResGCN) is constructed to fit the non-linear mappings from load graph to future loads. Besides, a graph concatenation method for parallel training is introduced to improve the learning efficiency. Using practical data in Houston, the annual, monthly, and daily effects of the crisis on power load are analyzed, which uncovers the strong correlation between the pandemic and the changes in regional electricity utilization. Moreover, the forecasting performance of the load graph-based ResGCN is validated by comparing with other representative methods. Its performance on MAPE and RMSE increased by 1.3264 and 15.03%, respectively. Codes related to all the simulations are available on & nbsp;https://github.com/YoungY6/ResGCN-for-Short-term-power-load-forecasting-under-COVID-19.

Power system load forecasting using mobility optimization and multi-task learning in COVID-19.

Affected by the new coronavirus (COVID-19) pandemic, global energy production and consumption have changed a lot. It is unknown whether conventional short-term load forecasting methods based on single-task, single-region, and conventional indicators can accurately capture the load pattern during the COVID-19 and should be carefully studied. In this paper, we make the following contributions: 1) A mobility-optimized load forecasting method based on multi-task learning and long short-term memory network is innovatively proposed to alleviate the impact of the COVID-19 on short-term load forecasting. The incorporation of mobility data and data sharing layers potentially reduces the difficulty of capturing the load patterns and improves the generalization of the load forecasting models. 2) The real public data collected from multiple agencies and companies in the United States and European countries are used to conduct horizontal and vertical tests. These tests prove the failure of the conventional models and methods in the COVID-19 and demonstrate the high accuracy (error mostly less than 1%) and robustness of the proposed model. 3) The Shapley additive explanations technology based on game theory is innovatively introduced to improve the objectivity of the models. It visualizes that mobility indicators are of great help to the accurate load forecasting. Besides, the non-synchronous relationships between the indicators' correlations and contributions to the load have been proved.