A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation

IEEE Transactions on Industrial Informatics, Journal Year: 2021, Volume and Issue: 17(10), P. 7050 - 7059

Published: Feb. 7, 2021

Predictions of renewable energy (RE) generation and electricity load are critical to smart grid operation. However, the prediction task remains challenging due intermittent chaotic character RE sources, diverse user behavior power consumers. This article presents a novel method for using improved stacked gated recurrent unit-recurrent neural network (GRU-RNN) both univariate multivariate scenarios. First, multiple sensitive monitoring parameters or historical consumption data selected according correlation analysis form input data. Second, GRU-RNN simplified GRU is constructed with training algorithm based on AdaGrad adjustable momentum. The modified structure enhance efficiency robustness. Third, used establish an accurate mapping between variables its self-feedback connections mechanism. proposed verified by two experiments: wind weather experimental results demonstrate that outperforms state-of-the-art methods machine learning deep in achieving effective

Language: Английский

---

Artificial Intelligence Techniques in Smart Grid: A Survey

Smart Cities, Journal Year: 2021, Volume and Issue: 4(2), P. 548 - 568

Published: April 22, 2021

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

Language: Английский

---

Methods and Models for Electric Load Forecasting: A Comprehensive Review

Logistics Supply Chain Sustainability and Global Challenges, Journal Year: 2020, Volume and Issue: 11(1), P. 51 - 76

Published: Feb. 1, 2020

Abstract Electric load forecasting (ELF) is a vital process in the planning of electricity industry and plays crucial role electric capacity scheduling power systems management and, therefore, it has attracted increasing academic interest. Hence, accuracy great importance for energy generating system management. This paper presents review methods models load. About 45 papers have been used comparison based on specified criteria such as time frame, inputs, outputs, scale project, value. The reveals that despite relative simplicity all reviewed models, regression analysis still widely efficient long-term forecasting. As short-term predictions, machine learning or artificial intelligence-based Artificial Neural Networks (ANN), Support Vector Machines (SVM), Fuzzy logic are favored.

Language: Английский

---

Blockchain and renewable energy: Integration challenges in circular economy era

Renewable Energy, Journal Year: 2021, Volume and Issue: 176, P. 183 - 197

Published: May 19, 2021

Language: Английский

---

Integrating Artificial Intelligence Internet of Things and 5G for Next-Generation Smartgrid: A Survey of Trends Challenges and Prospect

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 4794 - 4831

Published: Jan. 1, 2022

Smartgrid is a paradigm that was introduced into the conventional electricity network to enhance way generation, transmission, and distribution networks interrelate. It involves use of Information Communication Technology (ICT) other solution in fault intrusion detection, mere monitoring energy distribution. However, on one hand, actual earlier smartgrid, do not integrate more advanced features such as automatic decision making, security, scalability, self-healing awareness, real-time monitoring, cross-layer compatibility, etc. On emergence digitalization communication infrastructure support economic sector which among them are generation grid with Artificial Intelligence (AI) large-scale Machine (M2M) communication. With future Massive Internet Things (MIoT) pillars 5G/6G factory, it enabler next smart by providing needed platform integrates, addition infrastructure, AI IoT support, multitenant system. This paper aim at presenting comprehensive review research trends technological background, discuss futuristic next-generation driven artificial intelligence leverage 5G. In addition, discusses challenges smart-grids relate integration AI, 5G for better architecture. Also, proffers possible solutions some standards this novel trend. A corresponding work will dwell implementation discussed grid, using Matlab, NS2/NS3, Open-daylight Mininet soft tools compare related literature.

Language: Английский

---

A Comprehensive Review of Artificial Intelligence (AI) Companies in the Power Sector

Energies, Journal Year: 2023, Volume and Issue: 16(3), P. 1077 - 1077

Published: Jan. 18, 2023

There is an ongoing, revolutionary transformation occurring across the globe. This altering established processes, disrupting traditional business models and changing how people live their lives. The power sector no exception going through a radical of its own. Renewable energy, distributed energy sources, electric vehicles, advanced metering communication infrastructure, management algorithms, efficiency programs new digital solutions drive change in sector. These changes are fundamentally supply chains, shifting geopolitical powers revising landscapes. Underlying infrastructural components expected to generate enormous amounts data support these applications. Facilitating flow information coming from system′s prerequisite for applying Artificial Intelligence (AI) New components, flows AI techniques will play key role demand forecasting, system optimisation, fault detection, predictive maintenance whole string other areas. In this context, digitalisation becoming one most important factors sector′s process. Digital possess significant potential resolving multiple issues chain. Considering growing importance AI, paper explores current status technology’s adoption rate review conducted by analysing academic literature but also several hundred companies around world that developing implementing on grid’s edge.

Language: Английский

---

Enhancing Electrical Load Prediction Using a Bidirectional LSTM Neural Network

Electronics, Journal Year: 2023, Volume and Issue: 12(22), P. 4652 - 4652

Published: Nov. 15, 2023

Precise anticipation of electrical demand holds crucial importance for the optimal operation power systems and effective management energy markets within domain planning. This study builds on previous research focused application artificial neural networks to achieve accurate load forecasting. In this paper, an improved methodology is introduced, centering around bidirectional Long Short-Term Memory (LSTM) (NN). The primary aim proposed LSTM network enhance predictive performance by capturing intricate temporal patterns interdependencies time series data. While conventional feed-forward are suitable standalone data points, consumption characterized sequential dependencies, necessitating incorporation memory-based concepts. model designed furnish prediction framework with capacity assimilate leverage information from both preceding forthcoming steps. augmentation significantly bolsters capabilities encapsulating contextual understanding Extensive testing performed using multiple datasets, results demonstrate significant improvements in accuracy compared simpleRNN-based framework. successfully captures underlying dependencies data, achieving superior as gauged metrics such root mean square error (RMSE) absolute (MAE). outperforms models, a remarkable RMSE, attesting its forecast impending precision. extended contributes field leveraging forecasting accuracy. Specifically, BiLSTM’s MAE 0.122 demonstrates accuracy, outperforming RNN (0.163), (0.228), GRU (0.165) approximately 25%, 46%, 26%, best variation all networks, at 24-h step, while RMSE 0.022 notably lower than that (0.033), (0.055), respectively. findings highlight significance incorporating memory advanced architectures precise prediction. has potential facilitate more efficient planning market management, supporting decision-making processes systems.

Language: Английский

---

A holistic review on energy forecasting using big data and deep learning models

International Journal of Energy Research, Journal Year: 2021, Volume and Issue: 45(9), P. 13489 - 13530

Published: April 12, 2021

With the growth of forecasting models, energy is used for better planning, operation, and management in electric grid. It important to improve accuracy a faster decision-making process. Big data can handle large scale datasets extract patterns fed deep learning models that than traditional hence, recently started its application forecasting. In this study, an in-depth insight initially derived by investigating artificial intelligence (AI) machine (ML) techniques with their strengths weaknesses, enhancing consistency renewable integration modernizing overall However, Deep (DL) algorithms have capability big capturing inherent non-linear features through automatic feature extraction methods. Hence, extensive exhaustive review generative, hybrid, discriminative DL being examined short-term, medium-term, long-term energy, consumption, demand, supply etc. This study also explores different decomposition strategies build models. The recent success investigated, insights paradoxes parameter optimization during training model are identified. impact weather prediction wind solar detail. From existing literatures, it has seen average mean absolute percentage error (MAPE) value 10.29% 6.7% respectively. Current technology barriers involved implementing these recommendations overcome system An analysis, discussions results, scope improvement provided including potential directions future research

Language: Английский

---

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

Energy, Journal Year: 2021, Volume and Issue: 239, P. 122245 - 122245

Published: Oct. 5, 2021

Language: Английский

---

An adaptive backpropagation algorithm for long-term electricity load forecasting

Neural Computing and Applications, Journal Year: 2021, Volume and Issue: 34(1), P. 477 - 491

Published: Aug. 11, 2021

Language: Английский

---