Short-term residential load forecasting using Graph Convolutional Recurrent Neural Networks

Arastehfar, Sana; Matinkia, Mohammadjavad; Jabbarpour, Mohammad Reza

doi:10.1016/j.engappai.2022.105358

Cited by 37 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To better capture the long-term dependences in the sequence, two LTFEMs are stacked and added a max-pooling layer between them to further highlight the dominant feature. The calculation process from layer h to layer h + 1 is shown in Equations ( 18)- (20).…”

Section: Encoder-decodermentioning

confidence: 99%

“…Although the above methods have better learning ability when dealing with non-linear data than traditional prediction methods [19], they still have a large drawback in capturing longterm dependences. In recent years, more and more models are built using in-depth learning methods [20,21]. Recursive neural network (RNN) is one of the most common neural networks for time series data [18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid prediction method for short‐term load based on temporal convolutional networks and attentional mechanisms

Tian

Chen

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Accurate power load prediction is an important guide for power system planning and operation. High‐ or low‐load prediction results will affect the operation of the power system. In recent years, deep learning technology represented by convolution neural network (CNN) and transformer has been proved to be suitable for power load prediction. This paper proposes a new short‐term power load hybrid forecasting model, called channel enhanced attention (CEA) and temporal convolutional network (TCN)‐based transformer comprehensive forecasting model. This method combines the short‐term feature extraction ability of TCN with the long‐term dependent capture ability of transformer for short‐term load forecasting. And the CEA designed in this study is added to improve the prediction accuracy. On the same dataset, the designed model predicts power load mean square errors of 0.056 and 0.146 for the next 24 h and the next week, respectively, which is 0.002 to 0.073 and 0.012 to 0.024 lower than the baseline model. The experimental results show that the hybrid short‐term power load prediction model proposed in this paper is significantly better than the existing methods. The predicted curve is in agreement with the actual charge change, which provides a good guidance for short‐term power load prediction.

show abstract

Section: Encoder-decodermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A hybrid prediction method for short‐term load based on temporal convolutional networks and attentional mechanisms

Tian

Chen

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…Finally, for more works related to the load forecasting, refs. [53][54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70] A dataset can be created to train the deep learning-based application (e.g., the ANN) to forecast the values of the loads. Then, based on Figure 4, the current values and the historical values of the desired inputs can be used to predict the future values of power consumption in a cyber-physical microgrid using the trained ANN.…”

Section: Deep Learning-based Load Forecastingmentioning

confidence: 99%

Deep Learning for Forecasting-Based Applications in Cyber–Physical Microgrids: Recent Advances and Future Directions

et al. 2023

View full text Add to dashboard Cite

Renewable energy resources can be deployed locally and efficiently using the concept of microgrids. Due to the natural uncertainty of the output power of renewable energy resources, the planning for a proper operation of microgrids can be a challenging task. In addition, the information about the loads and the power consumption of them can create benefits to increase the efficiency of the microgrids. However, electrical loads can have uncertainty due to reasons such as unpredictable behavior of the consumers. To exploit a microgrid, energy management is required at the upper level of operation and control in order to reduce the costs. One of the most important tasks of the energy management system is to satisfy the loads and, in other words, develop a plan to maintain equilibrium between the power generation and power consumption. To obtain information about the output power of renewable energy resources and power consumption, deep learning can be implemented as a powerful tool, which is able to predict the desired values. In addition, weather conditions can affect the output power of renewable energy-based resources and the behavior of the consumers and, as a result, the power consumption. So, deep learning can be deployed for the anticipation of the weather conditions. This paper will study the recent works related to deep learning, which has been implemented for the prediction of the output power of renewable energy resources (i.e., PVs and wind turbines), electrical loads, and weather conditions (i.e., solar irradiance and wind speed). In addition, for possible future directions some strategies are suggested, the most important of which is the implementation of quantum computing in cyber–physical microgrids.

show abstract

“…The use of GNNs for assessing power system stability has been explored in [26], where the problem is formulated as a graph-level classification task to distinguish between rotor angle instability, voltage instability, and stability states, also based on power system topology and measurements. The paper [27] presents a hybrid neural network architecture which combines GNNs and RNNs to address the Short-Term Load Forecasting problem. The RNNs are used to process historical load data and provide inputs to GNNs, which are then used to extract the spatial information from users with similar consumption patterns, thus providing a more comprehensive approach to forecast the power consumption.…”

Section: Graph Neural Networkmentioning

confidence: 99%

Near Real-Time Distributed State Estimation via AI/ML-Empowered 5G Networks

Ognjen¹,

Forcan

Cosovic

et al. 2022

2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

Electric power systems consist of generation, distribution, and transmission systems, which are all traditionally coordinated from the corresponding control centres. System operators use specialized software solutions for monitoring and optimization of electric power systems, installed in control centres. Typical algorithms implemented in mentioned software solutions should satisfy near real-time operation requirements, while delivering accurate information for power system monitoring and optimizing its operation.Modern electric power systems have been increasing in size, complexity, as well as dynamics due to the growing integration of renewable energy resources, which have sporadic power generation. This necessitates the development of near real-time power system algorithms, demanding lower computational complexity regarding the power system size. Considering the growing trend in the collection of historical measurement data and recent advances in the rapidly developing deep learning field, the topic of this dissertation is the application of deep learning algorithms, namely graph neural networks (GNNs) and deep reinforcement learning (DRL), for monitoring and optimization of electric power systems.

show abstract

Short-term residential load forecasting using Graph Convolutional Recurrent Neural Networks

Cited by 37 publications

References 44 publications

A hybrid prediction method for short‐term load based on temporal convolutional networks and attentional mechanisms

A hybrid prediction method for short‐term load based on temporal convolutional networks and attentional mechanisms

Deep Learning for Forecasting-Based Applications in Cyber–Physical Microgrids: Recent Advances and Future Directions

Near Real-Time Distributed State Estimation via AI/ML-Empowered 5G Networks

Contact Info

Product

Resources

About