Recent Trends in Load Forecasting Technology for the Operation Optimization of Distributed Energy System

Su, Pengwei; Tian, Xiaobin; Yan, Wenjun; Deng, Shuai; Zhao, Jun; An, Qingsong; Wang, Yongzhen

doi:10.3390/en10091303

Cited by 35 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besarnya kebutuhan atau konsumsi energi listrik digambarkan dalam bentuk kurva yang dikenal sebagai kurva beban [1]. Kurva beban membentuk trend [2] yang berubah terhadap waktu membentuk pola beban yang berbeda-beda, tergantung pada beban pada jenis hari [3]; saat atau jam pembebanan [4]; musim; demografi dan ekonomi [5]. Trend penggunaan energi listrik bermanfaat untuk perencanaan pekerjaan untuk masa depan dan peramalan beban yang fokus secara teknis untuk waktu singkat (short term) dengan presisi tinggi.…”

Section: Pendahuluanunclassified

“…Pengembangan juga dapat dilakukan, dengan menggabungkan penyimpanan energi dan sistem distribusinya. Selain itu trend dapat pembentukan platform penjadwalan sistem pembangkitan energi listrik, pengaturan stok bahan bakar, termasuk prakiraan beban dan pasokan energi [6], simulasi sistem, analisis optimasi, bahkan membangun pusat interkoneksi [2] untuk penyaluran dan pengaturan penggunaan daya.…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Analisis Tren Konsumsi Energi Listrik pada Penyulang Singkarak

Yuniarti

Tara²,

Pratama³

et al. 2021

JSE

View full text Add to dashboard Cite

Electrical energy use is an interesting topic because it is related to the operational planning of the distribution system, maintenance of medium voltage networks, and prediction of electricity consumption, especially in the short term. Trends are created based on historical data represented in the load curves. This research aims to determine the characteristics of the load by making load groups according to the type of day and calculate the load factor based on secondary data from PT. PLN (Persero) Borang substation. The research uses comparative techniques in the load groups and calculates the load factor which is the benchmark for generation capacity. The results of the study showed that the load trendon Singkarak feeders in overall is the same on weekdays as on weekends, namely that minimum load occurs in the morning at 07.00, the load starts to increase but is not significant in relation to the activities of the population after 08.00-16.00. The load trend increases significantly from 16.00 to the peak load that occurs at 19.00-21.00 and after that, the load goes down to the minimum load. The trend for higher than average peak loads on Mondays is more common and weekend loads on Saturdays and Sundays only relatively small load fluctuationsoccur.. The load group for religious holidays and national holidays received good load factor scores, with a relatively small range of loads throughout the day.

show abstract

Section: Pendahuluanunclassified

Analisis Tren Konsumsi Energi Listrik pada Penyulang Singkarak

Yuniarti

Tara²,

Pratama³

et al. 2021

JSE

View full text Add to dashboard Cite

show abstract

“…A large number of authors utilized various forecasting techniques in several power system applications and research objectives. The most common forecasting techniques include time-series models, wavelet neural networks, regression methods, neural networks model, fuzzy logic, expert systems, and support vector machines (SVM) [20], [21], [26]. The timeseries models are comprised of various approaches such as autoregressive moving average (a combination of autoregressive and moving average models), autoregressive moving average with exogenous variables, autoregressive integrated moving average and autoregressive integrated moving average with exogenous variables [20], [21], [26].…”

Section: Related Previous Studiesmentioning

confidence: 99%

“…Some authors [19] used real-time load and ancillary support systems. Various forecasting techniques such as artificial neural networks, wavelet neural networks, time series, fuzzy logic, and support vector machine are used for many power systems studies [20], [21]. The studies are limited to the short-term [22] and long-term [23] load forecasting for power system planning and operation, electricity price and energy market behavior forecasting [8], [24], and hourly or day-ahead renewable energy forecast [7], [25] to manage the available power generation.…”

Section: Introductionmentioning

confidence: 99%

The Impact of Prediction Errors in the Domestic Peak Power Demand Management

Mahmud

Ravishankar

Hossain

et al. 2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

In this paper, the impact of prediction errors on the performance of a domestic power demand management is thoroughly investigated. Initially, a real-time peak power demand management system using battery energy storage systems (BESSs), electric vehicles (EVs) and photovoltaics (PV) systems is designed and modeled. The model uses real-time load demand of consumers and their roof-top PV power generation capability, and the charging-discharging constraints of BESSs and EVs to provide a coordinated response for peak power demand management. Afterwards, this real-time power demand management system is modeled using autoregressive moving average and artificial neural networks-based prediction techniques. The predicted values are used to provide a day-ahead peak power demand management decision. However, any significant error in the prediction process results in an incorrect energy sharing by the energy management system. In this research, two different customers connected to a real power distribution network with realistic load pattern and uncertainty are used to investigate the impact of this prediction error on the efficacy of an energy management system. The study shows that in some cases the prediction error can be more than 300 percent. The average capacity of energy support due to this prediction error can go up to 0.9 kWh, which increases battery charging-discharging cycles, hence reducing battery life and increasing energy cost. It also investigates a possible relationship between environmental conditions (solar insolation, temperature and humidity) and consumers' power demand. Considering the weather conditions, a day-ahead uncertainty detection technique is proposed for providing an improved power demand management.

show abstract

“…As of today, electric load forecasting is mainly conducted on the supply side of the energy sector. There, load forecasts are utilized to improve the information base and support the decision making process in the fields of energy purchasing, operations and maintenance or financial planning [13,14]. Although these applications already demonstrate the benefits of load forecasting, the potentials are underutilized in the manufacturing industry.…”

Section: Load Forecastingmentioning

confidence: 99%