A Lightweight Short-Term Photovoltaic Power Prediction for Edge Computing

Chang, Xiaomin; Li, Wei; Zomaya, Albert Y.

doi:10.1109/tgcn.2020.2996234

Cited by 25 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chang et al [102] proposed a training framework to obtain prediction models for predicting the power output of solar energy. Compared with the traditional scheme where training is carried out on a single machine, this lightweight framework is more energy-efficient and suitable for devices with constrained power and resources.…”

Section: Monitoring and Predictionmentioning

confidence: 99%

Edge Intelligence with Distributed Processing of DNNs: A Survey

Tang¹,

Cui²,

Qi³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

With the rapid development of deep learning, the size of data sets and deep neural networks (DNNs) models are also booming. As a result, the intolerable long time for models' training or inference with conventional strategies can not meet the satisfaction of modern tasks gradually. Moreover, devices stay idle in the scenario of edge computing (EC), which presents a waste of resources since they can share the pressure of the busy devices but they do not. To address the problem, the strategy leveraging distributed processing has been applied to load computation tasks from a single processor to a group of devices, which results in the acceleration of training or inference of DNN models and promotes the high utilization of devices in edge computing. Compared with existing papers, this paper presents an enlightening and novel review of applying distributed processing with data and model parallelism to improve deep learning tasks in edge computing. Considering the practicalities, commonly used lightweight models in a distributed system are introduced as well. As the key technique, the parallel strategy will be described in detail. Then some typical applications of distributed processing will be analyzed. Finally, the challenges of distributed processing with edge computing will be described.

show abstract

Section: Monitoring and Predictionmentioning

confidence: 99%

Edge Intelligence with Distributed Processing of DNNs: A Survey

Tang¹,

Cui²,

Qi³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…The comprehensive operational failure index is taken as the object, and the environmental characteristics such as wind speed and salt haze of the island are combined to predict. Then the prediction results are compared with LightGBM [26], XGBoost [27], and Bi‐Lstm [28] models.…”

Section: Case Studyingmentioning

confidence: 99%

A failure assessment method of island distribution lines based on model‐data hybrid drive

Zheng

Tang

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

Open circuit faults of island distribution lines account for more than 70% of the total number of faults in the distribution network. Failure assessment of lines plays a crucial role in the operational safety of the island distribution network. Aiming at the problems of multiple operational failure factors and difficulty in failure assessment, a failure assessment method of island distribution lines based on model-data hybrid drive is proposed in this paper. Specifically, in order to accurately describe the actual operating status and failure mechanism of distribution lines in the typical island environment, model-driven method is used to formulate a comprehensive operational failure index of distribution lines, which combines with the impact of strong wind and corrosion operation scenarios and the operating characteristics of lines. On this basis, to improve the accuracy of failure assessment under the influence of multiple factors in the island environment, an improved light gradient boosting machine model is constructed in a data-driven manner. Finally, based on actual data from distribution network in Zhoushan, China, the case study reveals that the proposed method could effectively assess the operational failure of island distribution lines.

show abstract

“…This rapid growth in the number of data centres gives rise to two issues [2]. The first is an increase in energy costs to service providers [3]. Statistical results [4] show that in 2018, the total power consumption of China's data centres was 150 billion kWh, accounting for 2% of the total social power consumption.…”

Section: Introductionmentioning

confidence: 99%

IECL: An Intelligent Energy Consumption Model for Cloud Manufacturing

Zhou

Shojafar

Alazab

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The high computational capability provided by a data centre makes it possible to solve complex manufacturing issues and carry out large-scale collaborative cloud manufacturing. Accurate, real-time estimation of the power required by a data centre can help resource providers predict the total power consumption and improve resource utilisation. To enhance the accuracy of server power models, we propose a real-time energy consumption prediction method called IECL that combines the support vector machine, random forest, and grid search algorithms. The random forest algorithm is used to screen the input parameters of the model, while the grid search method is used to optimise the hyperparameters. The error confidence interval is also leveraged to describe the uncertainty in the energy consumption by the server. Our experimental results suggest that the average absolute error for different workloads is less than 1.4% with benchmark models.

show abstract

A Lightweight Short-Term Photovoltaic Power Prediction for Edge Computing

Cited by 25 publications

References 19 publications

Edge Intelligence with Distributed Processing of DNNs: A Survey

Edge Intelligence with Distributed Processing of DNNs: A Survey

A failure assessment method of island distribution lines based on model‐data hybrid drive

IECL: An Intelligent Energy Consumption Model for Cloud Manufacturing

Contact Info

Product

Resources

About