A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting

Zhang, Wenyu; Chen, Qian; Yan, Junya; Xu, Jiyuan

doi:10.1016/j.energy.2021.121492

Cited by 70 publications

(23 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Initialize the PSO parameters as in table 3 and randomly generate the initial position and velocity of each particle following Eq. ( 11) and (12). Where r is a random number in the range of [0, 1], d is the dimension of particle i .…”

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

“…( 15), which is employed commonly to evaluate the fitting level of different models on the same testing set. The larger the value of 2 R is, the better the performance of forecasting for model is [12,55]. RMSE is formulated as Eq.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…In recent decades, electricity load forecasting has been classified into four forms according to the forecasting time windows: long-term [8,9], medium-term [10,11], short-term [2,12], and ultra-short-term load forecasting [13]. Short-term load forecasting (STLF) is usually used to perform one-day ahead to several-weeks ahead forecasting of electricity load [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

Huang¹,

Hasan

Deng³

et al. 2022

Energy

View full text Add to dashboard Cite

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

Huang¹,

Hasan

Deng³

et al. 2022

Energy

View full text Add to dashboard Cite

“…Since load forecasting is an important aspect of smart grids, a multitude of recent studies [13]- [15] based on several deep learning approaches have been conducted. However, most of these works focus on residential load forecasting.…”

Section: A Load Forecasting At Repsmentioning

confidence: 99%

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Husnoo¹,

Anwar²,

Hosseinzadeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

As Smart Meters are collecting and transmitting household energy consumption data to Retail Energy Providers (REP), the main challenge is to ensure the effective use of fine-grained consumer data while ensuring data privacy. In this manuscript, we tackle this challenge for energy load consumption forecasting in regards to REPs which is essential to energy demand management, load switching and infrastructure development. Specifically, we note that existing energy load forecasting is centralized, which are not scalable and most importantly, vulnerable to data privacy threats. Besides, REPs are individual market participants and liable to ensure the privacy of their own customers. To address this issue, we propose a novel horizontal privacy-preserving federated learning framework for REPs energy load forecasting, namely FedREP. We consider a federated learning system consisting of a control centre and multiple retailers by enabling multiple REPs to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security and scalability. For forecasting, we use a state-of-theart Long Short-Term Memory (LSTM) neural network due to its ability to learn long term sequences of observations and promises of higher accuracy with time-series data while solving the vanishing gradient problem. Finally, we conduct extensive data-driven experiments using a real energy consumption dataset. Experimental results demonstrate that our proposed federated learning framework can achieve sufficient performance in terms of MSE ranging between 0.3 to 0.4 and is relatively similar to that of a centralized approach while preserving privacy and improving scalability.

show abstract

“…The first drawback occurs when the model candidates change a little. For example, [29] only evaluates candidates' deep neural networks (DNN) such as multilayer perceptron (MLP), a convolutional neural network (CNN), and long short-term memory (LSTM). Ref.…”

Section: Introductionmentioning

confidence: 99%

Hyperparameter Optimization of Bayesian Neural Network Using Bayesian Optimization and Intelligent Feature Engineering for Load Forecasting

Zulfiqar

Gamage

Kamran

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper proposes a new hybrid framework for short-term load forecasting (STLF) by combining the Feature Engineering (FE) and Bayesian Optimization (BO) algorithms with a Bayesian Neural Network (BNN). The FE module comprises feature selection and extraction phases. Firstly, by merging the Random Forest (RaF) and Relief-F (ReF) algorithms, we developed a hybrid feature selector based on grey correlation analysis (GCA) to eliminate feature redundancy. Secondly, a radial basis Kernel function and principal component analysis (KPCA) are integrated into the feature-extraction module for dimensional reduction. Thirdly, the Bayesian Optimization (BO) algorithm is used to fine-tune the control parameters of a BNN and provides more accurate results by avoiding the optimal local trapping. The proposed FE-BNN-BO framework works in such a way to ensure stability, convergence, and accuracy. The proposed FE-BNN-BO model is tested on the hourly load data obtained from the PJM, USA, electricity market. In addition, the simulation results are also compared with other benchmark models such as Bi-Level, long short-term memory (LSTM), an accurate and fast convergence-based ANN (ANN-AFC), and a mutual-information-based ANN (ANN-MI). The results show that the proposed model has significantly improved the accuracy with a fast convergence rate and reduced the mean absolute percent error (MAPE).

show abstract

A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting

Cited by 70 publications

References 48 publications

Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Hyperparameter Optimization of Bayesian Neural Network Using Bayesian Optimization and Intelligent Feature Engineering for Load Forecasting

Contact Info

Product

Resources

About