A Hybrid Short-Term Load Forecasting Framework with an Attention-Based Encoder–Decoder Network Based on Seasonal and Trend Adjustment

Accurate electrical load forecasting plays an important role in power system operation. An effective load forecasting approach can improve the operation efficiency of a power system. This paper proposes the seasonal and trend adjustment attention encoder–decoder (STA–AED), a hybrid short-term load forecasting approach based on a multi-head attention encoder–decoder module with seasonal and trend adjustment. A seasonal and trend decomposing technique is used to preprocess the original electrical load data. Each decomposed datum is regressed to predict the future electric load value by utilizing the encoder–decoder network with the multi-head attention mechanism. With the multi-head attention mechanism, STA–AED can interpret the prediction results more effectively. A large number of experiments and extensive comparisons have been carried out with a load forecasting dataset from the United States. The proposed hybrid STA–AED model is superior to the other five counterpart models such as random forest, gradient boosting decision tree (GBDT), gated recurrent units (GRUs), Encoder–Decoder, and Encoder–Decoder with multi-head attention. The proposed hybrid model shows the best prediction accuracy in 14 out of 15 zones in terms of both root mean square error (RMSE) and mean absolute percentage error (MAPE).

Download Full-text

A Short-Term Load Forecasting Method Based on GRU-CNN Hybrid Neural Network Model

Mathematical Problems in Engineering ◽

10.1155/2020/1428104 ◽

2020 ◽

Vol 2020 ◽

pp. 1-10 ◽

Cited By ~ 3

Author(s):

Lizhen Wu ◽

Chun Kong ◽

Xiaohong Hao ◽

Wei Chen

Keyword(s):

Neural Network ◽

Power System ◽

Network Model ◽

Neural Network Model ◽

Feature Vector ◽

Load Forecasting ◽

Percentage Error ◽

Short Term ◽

Hybrid Neural Network ◽

Short Term Load Forecasting

Short-term load forecasting (STLF) plays a very important role in improving the economy and stability of the power system operation. With the smart meters and smart sensors widely deployed in the power system, a large amount of data was generated but not fully utilized, these data are complex and diverse, and most of the STLF methods cannot well handle such a huge, complex, and diverse data. For better accuracy of STLF, a GRU-CNN hybrid neural network model which combines the gated recurrent unit (GRU) and convolutional neural networks (CNN) was proposed; the feature vector of time sequence data is extracted by the GRU module, and the feature vector of other high-dimensional data is extracted by the CNN module. The proposed model was tested in a real-world experiment, and the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the GRU-CNN model are the lowest among BPNN, GRU, and CNN forecasting methods; the proposed GRU-CNN model can more fully use data and achieve more accurate short-term load forecasting.

Download Full-text

Analysis and evaluation of two short-term load forecasting techniques

International Journal of Emerging Electric Power Systems ◽

10.1515/ijeeps-2021-0051 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Saroj Kumar Panda ◽

Papia Ray

Keyword(s):

Neural Network ◽

Power System ◽

Deep Neural Network ◽

Load Forecasting ◽

Percentage Error ◽

Correlation Technique ◽

Short Term ◽

Efficient Operation ◽

Decision Mechanism ◽

Short Term Load Forecasting

Abstract Short-term load forecasting (STLF) is very important for an efficient operation of the power system because the exact and stable load forecasting brings good results to the power system. This manuscript presents the application of two new models in STLF i.e. Cross multi-models and second decision mechanism and Residential load forecasting in smart grid using deep neural network models. In the cross multi-model and second decision mechanism method, the horizontal and longitudinal load characteristics are useful for the construction of the model with the calculation of the total load. The dataset for this model is considered from Maine in New England, Singapore, and New South Wales of Australia. While, In the residential load forecasting method, the Spatio-temporal correlation technique is used for the construction of the iterative ResBlock and deep neural network which helps to give the characteristics of residential load with the use of a publicly available Redd dataset. The performances of the proposed models are calculated by the Root Mean Square Error, Mean Absolute Error, and Mean Absolute Percentage Error. From the simulation results, it is concluded that the performance of cross multi-model and second decision mechanism is good as compare to the residential load forecasting.

Download Full-text

Short Term Load Forecasting of Distribution Feeder Using Artificial Neural Network Technique

Journal of Informatics Electrical and Electronics Engineering (JIEEE) ◽

10.54060/jieee/002.01.002 ◽

2021 ◽

Vol 2 (1) ◽

pp. 1-22

Author(s):

Kumilachew Chane ◽

◽

Fsaha Mebrahtu Gebru ◽

Baseem Khan

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Load Forecasting ◽

Electric Utility ◽

Percentage Error ◽

Electrical Load ◽

Short Term ◽

Load Demand ◽

Short Term Load Forecasting ◽

Artificial Neural

This paper explains the load forecasting technique for prediction of electrical load at Hawassa city. In a deregulated market it is much need for a generating company to know about the market load demand for generating near to accurate power. If the generation is not sufficient to fulfill the demand, there would be problem of irregular supply and in case of excess generation the generating company will have to bear the loss. Neural network techniques have been recently suggested for short-term load forecasting by a large number of researchers. Several models were developed and tested on the real load data of a Finnish electric utility at Hawassa city. The authors carried out short-term load forecasting for Hawassa city using ANN (Artificial Neural Network) technique ANN was implemented on MATLAB and ETAP. Hourly load means the hourly power consumption in Hawassa city. Error was calculated as MAPE (Mean Absolute Percentage Error) and with error of about 1.5296% this paper was successfully carried out. This paper can be implemented by any intensive power consuming town for predicting the future load and would prove to be very useful tool while sanctioning the load.

Download Full-text

Short-Term Load Forecasting and Temperature Load Extraction Based on CEEMDAN and TDIC

CONVERTER ◽

10.17762/converter.305 ◽

2021 ◽

pp. 419-436

Author(s):

Min Wang Et al.

Keyword(s):

Dynamic Change ◽

Load Forecasting ◽

The United States ◽

Ensemble Empirical Mode Decomposition ◽

Percentage Error ◽

Time Data ◽

Short Term ◽

Multi Scale ◽

Temperature Load ◽

Short Term Load Forecasting

With the intensification of urbanization in various countries worldwide, the temperature load which is greatly affected by ambient temperature, such as summer cooling loads and winter heating loads, accounts for a rising proportion of the total urban load. It causes an increasing peak-to-valley load difference. However, due to the complex composition and strong randomness of the load, it is necessary to study the multi-scale and multi-period correlation between temperature. Based on this, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the temperature and load into multi-scale components. The time-dependent intrinsic correlation (TDIC) is proposed to analyze the local correlation between temperature and load in multiple periods under a multi-scale framework, and obtain the dynamic change characteristics of the correlation between temperature and load. Based on the TDIC analysis results, a suitable sample period for short-term load forecasting (STLF) and input temperature data can be selected. Finally, extreme learning machine optimized by particle swarm optimization (PSO-ELM) is used to forecast each component of the load. The proposed STLF method is validated on real-time data from the Pennsylvania-New Jersey-Maryland (PJM) Company in the United States. The proposed method has greatly reduced in both mean absolute percentage error (MAPE) and root mean square error (RMSE) compared with other traditional methods, and the temperature load that fluctuates with temperature in the day to be forecasted is extracted.

Download Full-text

Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting

Applied System Innovation ◽

10.3390/asi4030043 ◽

2021 ◽

Vol 4 (3) ◽

pp. 43

Author(s):

Yaju Rajbhandari ◽

Anup Marahatta ◽

Bishal Ghimire ◽

Ashish Shrestha ◽

Anand Gachhadar ◽

...

Keyword(s):

Time Series ◽

Power System ◽

Demand Forecasting ◽

Load Forecasting ◽

Load Flow ◽

Electricity Demand ◽

Working Environment ◽

Percentage Error ◽

Short Term ◽

Short Term Load Forecasting

Short-term electricity demand forecasting is one of the best ways to understand the changing characteristics of demand that helps to make important decisions regarding load flow analysis, preventing imbalance in generation planning, demand management, and load scheduling, all of which are actions for the reliability and quality of that power system. The variation in electricity demand depends upon various parameters, such as the effect of the temperature, social activities, holidays, the working environment, and so on. The selection of improper forecasting methods and data can lead to huge variations and mislead the power system operators. This paper presents a study of electricity demand and its relation to the previous day’s lags and temperature by examining the case of a consumer distribution center in urban Nepal. The effect of the temperature on load, load variation on weekends and weekdays, and the effect of load lags on the load demand are thoroughly discussed. Based on the analysis conducted on the data, short-term load forecasting is conducted for weekdays and weekends by using the previous day’s demand and temperature data for the whole year. Using the conventional time series model as a benchmark, an ANN model is developed to track the effect of the temperature and similar day patterns. The results show that the time series models with feedforward neural networks (FF-ANNs), in terms of the mean absolute percentage error (MAPE), performed better by 0.34% on a weekday and by 8.04% on a weekend.

Download Full-text