Short-Term Electricity Consumption Forecasting Based on the EMD-Fbprophet-LSTM Method

Short-term electricity consumption data reflects the operating efficiency of grid companies, and accurate forecasting of electricity consumption helps to achieve refined electricity consumption planning and improve transmission and distribution transportation efficiency. In view of the fact that the power consumption data is nonstationary, nonlinear, and greatly influenced by the season, holidays, and other factors, this paper adopts a time-series prediction model based on the EMD-Fbprophet-LSTM method to make short-term power consumption prediction for an enterprise's daily power consumption data. The EMD model was used to decompose the time series into a multisong intrinsic mode function (IMF) and a residual component, and then the Fbprophet method was used to predict the IMF component. The LSTM model is used to predict the short-term electricity consumption, and finally the prediction value of the combined model is measured based on the weights of the single Fbprophet and LSTM models. Compared with the single time-series prediction model, the time-series prediction model based on the EMD-Fbprophet-LSTM method has higher prediction accuracy and can effectively improve the accuracy of short-term regional electricity consumption prediction.

Download Full-text

A Time Series Prediction Model Based on Long Short-Term Memory Networks

10.1109/icsai53574.2021.9664063 ◽

2021 ◽

Author(s):

Linkai Wang ◽

Jing Chen ◽

Wei Wang ◽

Ruofan Wang ◽

Lina Yang ◽

...

Keyword(s):

Time Series ◽

Prediction Model ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Term Memory ◽

Model Based ◽

Long Short Term Memory

Download Full-text

An Electric Bus Power Consumption Model and Optimization of Charging Scheduling Concerning Multi-External Factors

Energies ◽

10.3390/en11082060 ◽

2018 ◽

Vol 11 (8) ◽

pp. 2060 ◽

Cited By ~ 14

Author(s):

Yajing Gao ◽

Shixiao Guo ◽

Jiafeng Ren ◽

Zheng Zhao ◽

Ali Ehsan ◽

...

Keyword(s):

Power Consumption ◽

Prediction Model ◽

Large Scale ◽

Operating Cost ◽

Electricity Consumption ◽

External Factors ◽

Electric Bus ◽

Consumption Data ◽

Power Consumption Prediction ◽

Consumption Prediction

With the large scale operation of electric buses (EBs), the arrangement of their charging optimization will have a significant impact on the operation and dispatch of EBs as well as the charging costs of EB companies. Thus, an accurate grasp of how external factors, such as the weather and policy, affect the electric consumption is of great importance. Especially in recent years, haze is becoming increasingly serious in some areas, which has a prominent impact on driving conditions and resident travel modes. Firstly, the grey relational analysis (GRA) method is used to analyze the various external factors that affect the power consumption of EBs, then a characteristic library of EBs concerning similar days is established. Then, the wavelet neural network (WNN) is used to train the power consumption factors together with power consumption data in the feature library, to establish the power consumption prediction model with multiple factors. In addition, the optimal charging model of EBs is put forward, and the reasonable charging time for the EB is used to achieve the minimum operating cost of the EB company. Finally, taking the electricity consumption data of EBs in Baoding and the data of relevant factors as an example, the power consumption prediction model and the charging optimization model of the EB are verified, which provides an important reference for the optimal charging of the EB, the trip arrangement of the EB, and the maximum profit of the electric public buses.

Download Full-text

A Novel Time Series Prediction Model Based on Deep Sparse Autoencoder

2018 37th Chinese Control Conference (CCC) ◽

10.23919/chicc.2018.8482990 ◽

2018 ◽

Cited By ~ 2

Author(s):

Meiling Xu ◽

Yaguo Dong ◽

Zhan Li ◽

Min Han ◽

Tong Xing

Keyword(s):

Time Series ◽

Prediction Model ◽

Time Series Prediction ◽

Model Based ◽

Sparse Autoencoder

Download Full-text

Electricity Consumption Prediction Based on Time Series Data Features Integrate with Long Short-Term Memory Model

Business Intelligence and Information Technology - Lecture Notes on Data Engineering and Communications Technologies ◽

10.1007/978-3-030-92632-8_80 ◽

2021 ◽

pp. 844-853

Author(s):

Jiaqiu Wang ◽

Hao Mou ◽

Hai Lin ◽

Yining Jin ◽

Ruijie Wang

Keyword(s):

Time Series ◽

Time Series Data ◽

Short Term Memory ◽

Electricity Consumption ◽

Memory Model ◽

Series Data ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Consumption Prediction

Download Full-text

Long Short-term Memory Network Prediction Model Based on Fuzzy Time Series

2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS) ◽

10.1109/icaiis49377.2020.9194902 ◽

2020 ◽

Author(s):

Hua Qu ◽

Jiaqi Li ◽

Yanpeng Zhang

Keyword(s):

Time Series ◽

Prediction Model ◽

Short Term Memory ◽

Fuzzy Time Series ◽

Short Term ◽

Term Memory ◽

Model Based ◽

Memory Network ◽

Network Prediction ◽

Long Short Term Memory

Download Full-text

Traffic Accident Time Series Prediction Model Based on Combination of ARIMA and BP and SVM

Journal of Traffic and Logistics Engineering ◽

10.18178/jtle.7.2.41-46 ◽

2019 ◽

pp. 41-46

Author(s):

Xiaorui Shao ◽

◽

Lester L Boey ◽

Yifei Luo

Keyword(s):

Time Series ◽

Prediction Model ◽

Traffic Accident ◽

Time Series Prediction ◽

Model Based

Download Full-text

Ultra-short-term prediction method of photovoltaic electric field power based on ground-based cloud image segmentation

E3S Web of Conferences ◽

10.1051/e3sconf/202018501052 ◽

2020 ◽

Vol 185 ◽

pp. 01052

Author(s):

Runjie Shen ◽

Ruimin Xing ◽

Yiying Wang ◽

Danqiong Hua ◽

Ming Ma

Keyword(s):

Power Generation ◽

Time Series ◽

Random Forest ◽

Prediction Model ◽

Power Plants ◽

Time Series Prediction ◽

Cloud Amount ◽

Continuous Model ◽

Short Term ◽

Photovoltaic Power

As a large number of photovoltaic power stations are built and put into operation, the total amount of photovoltaic power generation accounts for an increasing proportion of the total electricity. The inability to accurately predict solar energy output has brought great uncertainty to the grid. Therefore, predicting the future power of photovoltaic fields is of great significance. According to different time scales, predictions are divided into long-term, medium-term and ultra-short-term predictions. The main difficulty of ultra-short-term forecasting lies in the power fluctuations caused by sudden and drastic changes in environmental factors. The shading of clouds is directly related to the irradiance received on the surface of the photovoltaic panel, which has become the main factor affecting the fluctuation of photovoltaic power generation. Therefore, sky images captured by conventional cameras installed near solar panels can be used to analyze cloud characteristics and improve the accuracy of ultra-short-term predictions. This paper uses historical power information of photovoltaic power plants and cloud image data, combined with machine learning methods, to provide ultra-short-term predictions of the power generation of photovoltaic power plants. First, the random forest method is used to use historical power generation data to establish a single time series prediction model to predict ultra-short-term power generation. Compared with the continuous model, the root mean square (RMSE) error of prediction is reduced by 28.38%. Secondly, the Unet network is used to segment the cloud image, and the cloud amount information is analyzed and input into the random forest prediction model to obtain the bivariate prediction model. The experimental results prove that, based on the cloud amount information contained in the cloud chart, the bivariate prediction model has an 11.56% increase in prediction accuracy compared with the single time series prediction model, and an increase of 36.66% compared with the continuous model.

Download Full-text