Electricity load forecasting: a systematic review

Journal of Electrical Systems and Information Technology, Journal Year: 2020, Volume and Issue: 7(1)

Published: Sept. 9, 2020

Abstract The economic growth of every nation is highly related to its electricity infrastructure, network, and availability since has become the central part everyday life in this modern world. Hence, global demand for residential commercial purposes seen an incredible increase. On other side, prices keep fluctuating over past years not mentioning inadequacy generation meet demand. As a solution this, numerous studies aimed at estimating future electrical energy enable generators, distributors, suppliers plan effectively ahead promote conservation among users. Notwithstanding, load forecasting one major problems facing power industry inception electric power. current study tried undertake systematic critical review about seventy-seven (77) relevant previous works reported academic journals nine (2010–2020) forecasting. Specifically, attention was given following themes: (i) algorithms used their fitting ability field, (ii) theories factors affecting consumption origin research work, (iii) accuracy error metrics applied forecasting, (iv) period. results revealed that 90% out top models artificial intelligence based, with neural network (ANN) representing 28%. In scope, ANN were primarily short-term where patterns are complicated. Concerning used, it observed root-mean-square (RMSE) (38%) most metric forecasters, followed by mean absolute percentage MAPE (35%). further 50% based on weather parameters, 8.33% household lifestyle, 38.33% historical consumption, 3.33% stock indices. Finally, we recap challenges opportunities locally globally.

Language: Английский

---

N-BEATS neural network for mid-term electricity load forecasting

Applied Energy, Journal Year: 2021, Volume and Issue: 293, P. 116918 - 116918

Published: April 23, 2021

Language: Английский

---

Load Forecasting Models in Smart Grid Using Smart Meter Information: A Review

Energies, Journal Year: 2023, Volume and Issue: 16(3), P. 1404 - 1404

Published: Jan. 31, 2023

The smart grid concept is introduced to accelerate the operational efficiency and enhance reliability sustainability of power supply by operating in self-control mode find resolve problems developed time. In grid, use digital technology facilitates with an enhanced data transportation facility using sensors known as meters. Using these meters, various functionalities can be enhanced, such generation scheduling, real-time pricing, load management, quality enhancement, security analysis enhancement system, fault prediction, frequency voltage monitoring, forecasting, etc. From bulk generated a architecture, precise predicted before time support energy market. This supports operation maintain balance between demand generation, thus preventing system imbalance outages. study presents detailed review on forecasting category, calculation performance indicators, analyzing process for conventional meter information, used conduct task its challenges. Next, importance meter-based discussed along available approaches. Additionally, merits conducted over are articulated this paper.

Language: Английский

---

Data-driven key performance indicators and datasets for building energy flexibility: A review and perspectives

Applied Energy, Journal Year: 2023, Volume and Issue: 343, P. 121217 - 121217

Published: May 6, 2023

Energy flexibility, through short-term demand-side management (DSM) and energy storage technologies, is now seen as a major key to balancing the fluctuating supply in different grids with demand of buildings. This especially important when considering intermittent nature ever-growing renewable production, well increasing dynamics electricity paper provides holistic review (1) data-driven flexibility performance indicators (KPIs) for buildings operational phase (2) open datasets that can be used testing KPIs. The identifies total 81 KPIs from 91 recent publications. These were categorized analyzed according their type, complexity, scope, stakeholders, data requirement, baseline resolution, popularity. Moreover, 330 building collected evaluated. Of those, 16 deemed adequate feature performing response or building-to-grid (B2G) services. DSM strategy, grid control needed features, usability these selected analyzed. reveals future opportunities address limitations existing literature: developing new methodologies specifically evaluate strategies B2G services buildings; baseline-free could calculated easily accessible sensors meter data; (3) devoting non-engineering efforts promote such designing utility programs, standardizing quantification verification processes; (4) curating proper description assessments.

Language: Английский

---

Energy Forecasting: A Comprehensive Review of Techniques and Technologies

Energies, Journal Year: 2024, Volume and Issue: 17(7), P. 1662 - 1662

Published: March 30, 2024

Distribution System Operators (DSOs) and Aggregators benefit from novel energy forecasting (EF) approaches. Improved accuracy may make it easier to deal with imbalances between generation consumption. It also helps operations such as Demand Response Management (DRM) in Smart Grid (SG) architectures. For utilities, companies, consumers manage resources effectively educated decisions about consumption, EF is essential. many applications, Energy Load Forecasting (ELF), Generation (EGF), grid stability, accurate crucial. The state of the art examined this literature review, emphasising cutting-edge techniques technologies their significance for industry. gives an overview statistical, Machine Learning (ML)-based, Deep (DL)-based methods ensembles that form basis EF. Various time-series are explored, including sequence-to-sequence, recursive, direct forecasting. Furthermore, evaluation criteria reported, namely, relative absolute metrics Mean Absolute Error (MAE), Root Square (RMSE), Percentage (MAPE), Coefficient Determination (R2), Variation (CVRMSE), well Execution Time (ET), which used gauge prediction accuracy. Finally, overall step-by-step standard methodology often utilised problems presented.

Language: Английский

---

Optimal load forecasting and scheduling strategies for smart homes peer-to-peer energy networks: A comprehensive survey with critical simulation analysis

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102188 - 102188

Published: May 3, 2024

The home energy management (HEM) sector is going through an enormous change that includes important elements like incorporating green power, enhancing efficiency forecasting and scheduling optimization techniques, employing smart grid infrastructure, regulating the dynamics of optimal trading. As a result, ecosystem players need to clarify their roles, develop effective regulatory structures, experiment with new business models. Peer-to-Peer (P2P) trading seems be one viable options in these conditions, where consumers can sell/buy electricity to/from other users prior totally depending on utility. P2P enables exchange between prosumers, thus provide more robust platform for This strategy decentralizes market than it did previously, opening up possibilities improving trade customers Considering above scenarios, this research provides extensive insight structure, procedure, design, platform, pricing mechanism, approaches, topologies possible futuristic while examining characteristics, pros cons primary goal determining whichever approach most appropriate given situation HEMs. Moreover, HEMs load framework simulation model also proposed analyze network critically, paving technical directions scientific researchers. With cooperation, age technological advancements ushering intelligent, interconnected, reactive urban environment are brought life. In sense, path living entails reinventing as well how people interact perceive dwellings larger city. Finally, work comprehensive overview challenges terms strategies, solutions, future prospects.

Language: Английский

---

ARIMA Models in Electrical Load Forecasting and Their Robustness to Noise

Energies, Journal Year: 2021, Volume and Issue: 14(23), P. 7952 - 7952

Published: Nov. 28, 2021

The paper addresses the problem of insufficient knowledge on impact noise auto-regressive integrated moving average (ARIMA) model identification. work offers a simulation-based solution to analysis tolerance ARIMA models in electrical load forecasting. In study, an idealized obtained from real data Polish power system was disturbed by different levels. then re-identified, its parameters were estimated, and new forecasts calculated. experiment allowed us evaluate robustness their ability predict time series. It could be concluded that reaction random disturbances modeled series relatively weak. limiting level at which forecasting collapsed determined. results highlight key role preprocessing stage mining learning. They contribute more accurate decision making uncertain environment, help shape energy policy, have implications for sustainability reliability systems.

Language: Английский

---

Long-Term Forecasting of Electrical Loads in Kuwait Using Prophet and Holt–Winters Models

Applied Sciences, Journal Year: 2020, Volume and Issue: 10(16), P. 5627 - 5627

Published: Aug. 13, 2020

The rapidly increasing population growth and expansion of urban development are undoubtedly two the main reasons for global energy consumption. Accurate long-term forecasting peak load is essential saving time money countries’ power generation utilities. This paper introduces first investigation into performance Prophet model in Kuwait. compared with well-established Holt–Winters to assess its feasibility accuracy loads. Real data electric peaks from Kuwait powerplants 2010 2020 were used peaks, between 2030. has shown more accurate predictions than five statistical metrics. Besides, robustness models was investigated by adding Gaussian white noise different intensities. proven be robust model. Furthermore, generalizability test that outperforms reported results suggest forecasted maximum expected reach 18,550 19,588 MW 2030 study suggests best months scheduling preventive maintenance year 2021 November until March both models.

Language: Английский

---

Transformer-Based Model for Electrical Load Forecasting

Energies, Journal Year: 2022, Volume and Issue: 15(14), P. 4993 - 4993

Published: July 8, 2022

Amongst energy-related CO2 emissions, electricity is the largest single contributor, and with proliferation of electric vehicles other developments, energy use expected to increase. Load forecasting essential for combating these issues as it balances demand production contributes management. Current state-of-the-art solutions such recurrent neural networks (RNNs) sequence-to-sequence algorithms (Seq2Seq) are highly accurate, but most studies examine them on a data stream. On hand, in natural language processing (NLP), transformer architecture has become dominant technique, outperforming RNN Seq2Seq while also allowing parallelization. Consequently, this paper proposes transformer-based load by modifying NLP workflow, adding N-space transformation, designing novel technique handling contextual features. Moreover, contrast studies, we evaluate proposed solution different streams under various horizons input window lengths order ensure result reproducibility. Results show that approach successfully handles time series outperforms models.

Language: Английский

---

Techno-economic and environmental evaluation of PV/diesel/battery hybrid energy system using improved dispatch strategy

Energy Reports, Journal Year: 2022, Volume and Issue: 8, P. 6794 - 6814

Published: May 25, 2022

The selection of an appropriate dispatch strategy is considered as a major concern when designing hybrid energy system (HES) since it has large effects on the stability, reliability, environmental and economic performance system. cycle charging (CC) default in HOMER software. However, main drawback this that uses resource load data current time step no information about future. This paper aims to investigate optimum design off-grid PV/diesel/battery HES for electrifying rural area Iraq. A new which 12-hour foresight solar production developed using MATLAB Link module comparison between proposed carried out by considering technical, economic, performance. results show achieves better than CC having NPC $4.03M, renewable fraction 41.3% CO2 emissions 851377 kg/year. For strategy, these values are calculated $4.19M, 33.9% 957477 kg, respectively. sensitivity analysis also performed reduce effect input parameters optimization determine critical parameters. research findings can play crucial role development more effective management systems.

Language: Английский

---