Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid

Hafeez, Ghulam; Alimgeer, Khurram Saleem; Khan, Imran

doi:10.1016/j.apenergy.2020.114915

Cited by 201 publications

(62 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised neural networks-such as restricted Boltzmann machine, autoencoder, and variational autoencoder-are applied to anomaly detection [39,40], stability assessment [41], load forecasting [42][43][44], and so on. Clustering is the unsupervised task of grouping the population or data points into a set of groups, in which data in the same groups are similar to each other.…”

Section: Unsupervised Learningmentioning

confidence: 99%

“…Dimensional reduction (DR) techniques, which transform the data from a high-dimensional space to a low-dimensional space, are often required when processing smart grid data to reduce redundant features. Some of the DR methods commonly used in the smart grid [43,[49][50][51] include principal component analysis (PCA), linear discriminant analysis, generalized discriminant analysis, and non-negative matrix factorization.…”

Section: Unsupervised Learningmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Techniques in Smart Grid: A Survey

2021

View full text Add to dashboard Cite

The smart grid is enabling the collection of massive amounts of high-dimensional and multi-type data about the electric power grid operations, by integrating advanced metering infrastructure, control technologies, and communication technologies. However, the traditional modeling, optimization, and control technologies have many limitations in processing the data; thus, the applications of artificial intelligence (AI) techniques in the smart grid are becoming more apparent. This survey presents a structured review of the existing research into some common AI techniques applied to load forecasting, power grid stability assessment, faults detection, and security problems in the smart grid and power systems. It also provides further research challenges for applying AI technologies to realize truly smart grid systems. Finally, this survey presents opportunities of applying AI to smart grid problems. The paper concludes that the applications of AI techniques can enhance and improve the reliability and resilience of smart grid systems.

show abstract

Section: Unsupervised Learningmentioning

confidence: 99%

Section: Unsupervised Learningmentioning

confidence: 99%

Artificial Intelligence Techniques in Smart Grid: A Survey

2021

View full text Add to dashboard Cite

show abstract

“…So, it would be beneficial to reduce the computation times for load forecasting in the smart grid. Due to the disadvantages of BP, non-BP based works have been proposed for load forecasting [44] [46] [49]. In other application areas, alternative approaches to BP are also being investigated [28] [151] [152] [153].…”

Section: Deep Learning Process Contains Artificialmentioning

confidence: 99%

“…It was also found that LSTM is the most widely used ANN technique for load forecasting. For purposes such as improving feature selection [49], feature extraction [78], computational time [84], etc., LSTM has been found to provide more impactful outputs than other ANN techniques [40] [50] [53] (Table IV). BPNN was the next most used technique for load forecasting.…”

Section: B Different Ann Techniques In Deep Learning Based Load Forementioning

confidence: 99%

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

Load forecasting is a vital part of smart grids for predicting the required electrical power using artificial intelligence (AI). Deep learning is broadly used for load forecasting in the smart grid using the artificial neural network (ANN). Generally, computing the deep learning in the smart grid requires massive data aggregation or centralization and significant computational time. This paper presents a survey of deep learning-based load forecasting techniques from 2015 to 2020. This survey discusses the studies based on their deep learning techniques, Distributed Deep Learning (DDL) techniques, Back Propagation (BP) based works, and non-BP based works in the load forecasting process. Consequent to the survey, it was determined that data aggregation dependency would be beneficial for reducing computational time in load forecasting. Therefore, a conceptual model of DDL for smart grids has been presented, where the HSIC (Hilbert-Schmidt Independence Criterion) Bottleneck technique has been incorporated to provide higher accuracy.

show abstract

“…In order to meet the demand of the consumers, balance has to be maintained or consequently consumers will face short term outages. To optimally balance the demand with supply, electric load forecasting is mandatory [4]. By installing demand-side load management (DSLM) in smart meters at consumers' premises, the system will get the demand response (DR) of a consumer which will help to adjust the energy demand with the fluctuating generation [5].…”

Section: Introductionmentioning

confidence: 99%

Closed-Loop Elastic Demand Control under Dynamic Pricing Program in Smart Microgrid Using Super Twisting Sliding Mode Controller

Khan

Ullah

Hafeez

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Electricity demand is rising due to industrialisation, population growth and economic development. To meet this rising electricity demand, towns are renovated by smart cities, where the internet of things enabled devices, communication technologies, dynamic pricing servers and renewable energy sources are integrated. Internet of things (IoT) refers to scenarios where network connectivity and computing capability is extended to objects, sensors and other items not normally considered computers. IoT allows these devices to generate, exchange and consume data without or with minimum human intervention. This integrated environment of smart cities maintains a balance between demand and supply. In this work, we proposed a closed-loop super twisting sliding mode controller (STSMC) to handle the uncertain and fluctuating load to maintain the balance between demand and supply persistently. Demand-side load management (DSLM) consists of agents-based demand response (DR) programs that are designed to control, change and shift the load usage pattern according to the price of the energy of a smart grid community. In smart grids, evolved DR programs are implemented which facilitate controlling of consumer demand by effective regulation services. The DSLM under price-based DR programs perform load shifting, peak clipping and valley filling to maintain the balance between demand and supply. We demonstrate a theoretical control approach for persistent demand control by dynamic price-based closed-loop STSMC. A renewable energy integrated microgrid scenario is discussed numerically to show that the demand of consumers can be controlled through STSMC, which regulates the electricity price to the DSLM agents of the smart grid community. The overall demand elasticity of the current study is represented by a first-order dynamic price generation model having a piece-wise linear price-based DR program. The simulation environment for this whole scenario is developed in MATLAB/Simulink. The simulations validate that the closed-loop price-based elastic demand control technique can trace down the generation of a renewable energy integrated microgrid.

show abstract

Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid

Cited by 201 publications

References 55 publications

Artificial Intelligence Techniques in Smart Grid: A Survey

Artificial Intelligence Techniques in Smart Grid: A Survey

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

Closed-Loop Elastic Demand Control under Dynamic Pricing Program in Smart Microgrid Using Super Twisting Sliding Mode Controller

Contact Info

Product

Resources

About