Load Photo: A Novel Analysis Method for Load Data

Wang, Hong; Qi, Linhai; Yan, Lei; Li, Zuyi

doi:10.1109/tsg.2020.3025936

Cited by 11 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, deep learning can determine the locations of the meters to monitor the power quality of the power grid in [65]. With the measurements from the meters, CNN was adopted to perform load analysis in [66]. The meters in the smart grid may belong to different entities.…”

Section: Application Of Deep Learning In the Smart Gridmentioning

confidence: 99%

Intelligent Charging Management of Electric Vehicles Considering Dynamic User Behavior and Renewable Energy: A Stochastic Game Approach

Chung

Maharjan

Zhang

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

The current energy system is changing, mainly due to the rise of global energy consumption and the depletion of fossil energy sources. Regarding the electric power system, such changes constitute a significant challenge to the electricity grids and call for the development of smart grids. The smart grid is capable of monitoring individual energy consumption, integrating renewable energy, and supporting twoway communication between the grid operators and the customers. Moreover, to meet the requirement of the Paris Agreement, which predicts that the world needs to reduce 1170 giga tons of the cumulative CO 2 emissions between 2015 and 2100, promoting electric vehicles (EVs) and installing renewable energy resources are two main trends in policy making to reduce our dependency on fossil fuel resources. With more and more installation of renewable energy resources, uncertainties associated with renewable energy generation should be addressed when operating the smart grid. That is, weather conditions may influence renewable energy production, and therefore the controllability of that production is not the same as the conventional power generators for the grid operator. Other than the uncertainties associated with renewable energy generation, the maintenance of the generators raises a new challenge to the operator as the renewable energy generators are usually placed at locations with hazardous environments.Apart from the operator side, customers on the traditional power grid can install renewable energy resources in their households (e.g., solar panels on the rooftop). Therefore, customers can be separated into two categories in the smart grid, namely consumers and prosumers. The consumers only consume energy, and the prosumers can both consume and produce energy. The renewable energy production of the prosumers may be larger than their own consumption, and therefore they may want to sell their energy surplus. However, the price of selling energy to the external market is lower than the spot price in the external market. Therefore, peer-to-peer (P2P) energy trading is a much more attractive alternative than selling surplus generation in the external market. The electricity prices in the external market are generated in real time so that both the consumers and the prosumers also need to consider the uncertainty related to electricity prices to form the best strategies. By doing so, the consumers can obtain the minimum electricity costs, and the iii iv Chapter 0 prosumers can increase their revenue.Another method for reducing CO 2 emissions is to promote EVs. However, charging a huge number of EVs simultaneously may cause a sudden increase in energy consumption, and therefore the charging tasks of EVs must be controlled to avoid consuming a considerable amount of energy from the power grid in a short time. Although energy production from renewable energy resources can relieve this situation, the deployment of renewable energy sources cannot satisfy the surge for more energy from an increasing number of EVs. To this end...

show abstract

Section: Application Of Deep Learning In the Smart Gridmentioning

confidence: 99%

Intelligent Charging Management of Electric Vehicles Considering Dynamic User Behavior and Renewable Energy: A Stochastic Game Approach

Chung

Maharjan

Zhang

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…Compared with regular CNN networks, an LSTM network is more suitable for processing classification or prediction of time-series data. By introducing a gate structure, an LSTM neural network has greater selectivity compared with traditional recursive neural networks [12][13][14][15][16][17][18][19][20][21][22][23]. In this paper, a neural network model based on the Aquila optimization algorithm combined with a neural network prediction model is proposed to speed up the prediction speed of the neural network and improve the prediction accuracy and speed of photovoltaic power systems.…”

Section: Introductionmentioning

confidence: 99%

Research on a Photovoltaic Power Prediction Model Based on an IAO-LSTM Optimization Algorithm

Liu

Yang

2023

Processes

View full text Add to dashboard Cite

With the rapid popularization and development of renewable energy, solar photovoltaic power generation systems have become an important energy choice. Convolutional neural network (CNN) models have been widely used in photovoltaic power forecasting, with research focused on problems such as long training times, forecasting accuracy and insufficient speed, etc. Using the advantages of swarm intelligence algorithms such as global optimization, strong adaptability and fast convergence, the improved Aquila optimization algorithm (AO) is used to optimize the structure of neural networks, and the optimal solution is chosen as the structure of neural networks used for subsequent prediction. However, its performance in processing sequence data with time characteristics is not good, so this paper introduces a Long Short-Term Memory (LSTM) neural network which has obvious advantages in time-series analysis. The Cauchy variational strategy is used to improve the model, and then the improved Aquila optimization algorithm (IAO) is used to optimize the parameters of the LSTM neural network to establish a model for predicting the actual photovoltaic power. The experimental results show that the proposed IAO-LSTM photovoltaic power prediction model has less error, and its overall quality and performance are significantly improved compared with the previously proposed AO-CNN model.

show abstract

“…In recent years, data-driven generative models such as generative adversarial networks (GAN) (Goodfellow et al, 2014) have enabled the modeling of power systems without models. GAN was first introduced to renewable scenario generation in (Chen et al, 2018), and has been used in load generation (Wang et al, 2021), reconstruction of high-temporal-resolution PV generation data (Zhang et al, 2021), etc. Besides, GAN has also been introduced to generating electroencephalographic data (Debie et al, 2020), spatial-temporal data (Qu et al, 2020), and sensitive data in IIoT operations (Hindistan and Yetkin, 2023), etc.…”

Section: Introductionmentioning

confidence: 99%

A data-driven approach for generating load profiles based on InfoGAN and MKDE

Lan,

Zhou,

Guo

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

High-quality demand-side management requires an abundance of load profiles to support decision-making processes. However, customer energy consumption data often contains sensitive personal information, and service providers face significant challenges in accessing a substantial amount of energy consumption data. To generate a large volume of customer data without compromising privacy, this study introduces a data-driven approach integrating Information Maximizing Generative Adversarial Networks (InfoGAN) with Multivariate Kernel Density Estimation (MKDE) for the generation of load profiles. InfoGAN is firstly trained based on existing customer load profiles, with the Q network disentangling the load into feature variables and the generator producing realistic profiles. Subsequently, MKDE is utilized to assess the distribution of these features, enabling the generation of new profiles by sampling new feature variables. The proposed method circumvents the need for intricate sampling or modeling processes and generates realistic data that represents the inherent uncertainties and fluctuations characterizing customers’ electricity consumption. The generated data could be used as the substitution for real electricity consumption data, thereby facilitating further applications without compromising privacy concerns.

show abstract

Load Photo: A Novel Analysis Method for Load Data

Cited by 11 publications

References 46 publications

Intelligent Charging Management of Electric Vehicles Considering Dynamic User Behavior and Renewable Energy: A Stochastic Game Approach

Intelligent Charging Management of Electric Vehicles Considering Dynamic User Behavior and Renewable Energy: A Stochastic Game Approach

Research on a Photovoltaic Power Prediction Model Based on an IAO-LSTM Optimization Algorithm

A data-driven approach for generating load profiles based on InfoGAN and MKDE

Contact Info

Product

Resources

About