An attention‐based
            <scp>CNN‐LSTM‐BiLSTM</scp>
            model for short‐term electric load forecasting in integrated energy system

Wu, Kunpeng; Wu, Jian; Liang, Feng; Yang, Bo; Rong, Lei; Yang, Shenquan; Zhao, Ren

doi:10.1002/2050-7038.12637

Cited by 102 publications

(45 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of the bidirectional long-term memory network improves the network's ability to learn historical data, but it also leads to slow network prediction and different effects. Choosing different curves to predict whether to use a Bi-LSTM can save prediction time while ensuring prediction accuracy [22].…”

Section: Hyperparameter Optimization Of Lstmmentioning

confidence: 99%

Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM

et al. 2021

View full text Add to dashboard Cite

The effective prediction of bus load can provide an important basis for power system dispatching and planning and energy consumption to promote environmental sustainable development. A bus load forecasting method based on variational modal decomposition (VMD) and bidirectional long short-term memory (Bi-LSTM) network was proposed in this article. Firstly, the bus load series was decomposed into a group of relatively stable subsequence components by VMD to reduce the interaction between different trend information. Then, a time series prediction model based on Bi-LSTM was constructed for each sub sequence, and Bayesian theory was used to optimize the sub sequence-related hyperparameters and judge whether the sequence uses Bi-LSTM to improve the prediction accuracy of a single model. Finally, the bus load prediction value was obtained by superimposing the prediction results of each subsequence. The example results show that compared with the traditional prediction algorithm, the proposed method can better track the change trend of bus load, and has higher prediction accuracy and stability.

show abstract

Section: Hyperparameter Optimization Of Lstmmentioning

confidence: 99%

Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Zhen et al proposed an algorithm based on long and short-term memory network and convolutional neural network (LCWSnet), which uses leg Euler angle information to diagnose and classify gait abnormalities, and can adaptively adjust feature-related parameters [20]. The attention mechanism can devote more attention to important areas to obtain more detailed information and suppress other useless information [22]. Chen et al proposed an attention-based CNN-LSTM method for sleep awakening detection using heterogeneous sensor data, with a significant improvement from 5% to 46% [23].…”

Section: Introductionmentioning

confidence: 99%

An Attention-Based CNN-LSTM Model with Limb Synergy for Joint Angles Prediction

Zhu

Liu

Meng

et al. 2021

2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

Gait prediction is crucial in exoskeleton-assisted gait rehabilitation by recognizing the movement intention of patients, so as to realize the adaptive and transparent robotic assistance. Human locomotion has inherent synergies and coordination, and the dynamic mapping of the upper and lower limbs is beneficial to improve the prediction accuracy. Current prediction methods did not consider the correlation of gait data in time and space, resulting in a large amount of redundant data and low prediction accuracy. This paper proposes a gait trajectory prediction method based on convolutional neural network-long short-term memory (CNN-LSTM) model, which predicts the human knee/ankle joint trajectory based on upper and lower limb collaborative data. The attention mechanism is applied to determine which dimensions are essential in gait prediction, so the accuracy can be improved by adopting key elements. Results show that, within a predicted horizon of 50ms, the prediction RMSE is as low as 0.317 degrees.

show abstract

“…[23] evaluates several different models and discusses each model's ability to accurately forecast hourly heating, cooling, and electrical loads for a district energy system up to 24 h in advance using weather and time variables (month, hour, and day) as inputs. [24] takes the historical load, temperature, cooling load, and gas consumption in the recent five days as input characteristics. CNN combined with attention block is used to extract the effective characteristics of load influence factors to forecast the next hour's load.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Electric Load Forecasting of Integrated Energy System Considering Nonlinear Synergy Between Different Loads

Wang

2021

IEEE Access

View full text Add to dashboard Cite

As an efficient form of energy utilization, an integrated energy system integrates oil, natural gas, coal, and other energy sources and converts them into electric, cooling, and heating for users through energy conversion devices. In this process, integrated energy service providers need to make energy conversion decisions based on users' demand information feedback. Therefore, there is uncertainty and coupling between the electric cooling and heating loads, making it difficult to forecast the loads accurately. Firstly, this paper analyzes the integrated energy system's energy consumption characteristics and the interaction mechanism between the supply and demand sides, which fundamentally explains the coupling relationship between different loads of the integrated energy system. Secondly, REC, DEC, REH, and DEH are constructed from electric cooling and heating loads. The relationship between electric load and cooling and heating load is analyzed by a scatter distribution diagram and maximum information coefficient method. The nonlinear correlation between electric load and cooling and heating loads is proved. Based on this, the integrated energy system's synergetic electric load forecasting formula reflecting the nonlinear synergistic effect between loads is proposed. Finally, based on stacking ensemble learning, an integrated energy system electric load forecasting model considering the nonlinear synergy between loads is established by integrating BP neural network, support vector regression, random forest, and gradient boosting decision tree. Through the experimental analysis of the Arizona State University Tempe campus's integrated energy system project, it is found that the effect of the synergistic quadratic forecasting is better than that of the primary forecasting. Besides, the MAPE of the quadratic synergistic forecasting formula is lower than that of the other two forms, indicating that the proposed synergistic electric load forecasting formula considering the nonlinear synergy between loads can improve the accuracy of electric load forecasting of the integrated energy system.INDEX TERMS energy consumption characteristics, integrated energy system, synergetic forecasting, Stacking ensemble learning.

show abstract

An attention‐based CNN‐LSTM‐BiLSTM model for short‐term electric load forecasting in integrated energy system

Cited by 102 publications

References 31 publications

Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM

Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM

An Attention-Based CNN-LSTM Model with Limb Synergy for Joint Angles Prediction

Short-Term Electric Load Forecasting of Integrated Energy System Considering Nonlinear Synergy Between Different Loads

Contact Info

Product

Resources

About