Short-Term Load Forecasting Using Soft Computing Techniques

Chaturvedi, D. K.; Premdayal, Sinha Anand; Chandiok, Ashish

doi:10.4236/ijcns.2010.33035

Cited by 16 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNG station load also lies in this category. If we add these spikes in the training data of ANN model then the average error of the model becomes very high [16]. …”

mentioning

confidence: 99%

Factor Affecting Short Term Load Forecasting

Fahad¹,

Arbab²

2014

JOCET

View full text Add to dashboard Cite

Abstract-The basic objective of short term load forecasting is to predict the near future load for example next hour load prediction or next day load prediction etc. The total system load is the load seen at the generating end of the power system, which includes the sum of all types of loads connected to the system plus the losses. To design efficient and accurate forecasting model one must have good understanding of the characteristics of the system. There are various factors which influence the behavior of the consumer load and also impact the total losses in transmission lines. These factors can be categorized as Time factor, weather, economy and random disturbances. In this research paper these factors and their impact on consumption of electric power and their significance in short term load forecasting is evaluated.Index Terms-ANN, factors of STLF, load forecasting, load prediction. I. TIME FACTORTime is the most important factor in short term load forecasting because its impact on consumer load is highest. From observing load curve of several different grid stations it is found that the load curve has "time of the day" property, also it has "day of week", "week of month" and "month of season" property. This means that load curve is periodic in nature. Fig. 1(a)- Fig. 1(c) shows the load curve of 3 Fridays of the April 2012.As can be seen in Fig. 1(a)- Fig. 1(c) that although the average load is different because of the difference of temperature during each day but the pattern of the load is nearly same. In each curve there arises three peaks First peak at 8 o clock, 2 nd peak at 12:30 pm, And third at 8 pm and in curves first peak is lowest 2 nd a bit taller and third the highest. This shows periodicity in terms of day of the week. Manuscript received August 17, 2013; revised December 16, 2013. This work was carried out as a final year project for the award of MS degree in electrical engineering.Muhammad Usman Fahad is with the University of Engineering and Technology, Peshawar,.Naeem Arbab is with the Electrical Engineering Department of University of Engineering and Technology, Peshawar, Pakistan (e-mail: mnarbab01@yahoo.com). From the observation of daily load curve of any grid station it can be seen that load variation follows certain rules with the "time point" of the day.In Fig. 2 hourly load curves is shown for 24 hours of a day in winter season. The interval length is one hour, so there are 24 intervals in the figure. It can be seen in figure that the load is low and stable from 0 am to 6 am (0am means 12 o clock at night), the load start rising at 7 o clock till 9 am and then it is flattened till 12 am and after that it descends till 5 pm (17:00 in figure) and after 5 pm it start rising till 8 pm (19:00), after 8 pm load gradually decrease again until the end of the day.It can be seen in Fig. 2 that maximum demand occurs at 8pm, and minimum load demand occurs after mid night. So if we closely observe this load curve it can be seen that load demand reflects the consumer's daily life style. At mid...

show abstract

“…CNG station load also lies in this category. If we add these spikes in the training data of ANN model then the average error of the model becomes very high [16]. …”

mentioning

confidence: 99%

Factor Affecting Short Term Load Forecasting

Fahad¹,

Arbab²

2014

JOCET

View full text Add to dashboard Cite

show abstract

“…There are many load forecasting methods that have been reported over the last decade from simple persistence based methods [24], which select historical data from a similar day for use as a prediction, to more complex methods such as those using mathematical models with time series, artificial neural networks, fuzzy logic, expert systems or statistical learning algorithms [48,49]. In this work, a time series method based autoregressive model (AR) is used to predict the load and PV generation profiles.…”

Section: Load and Pv Energy Forecastingmentioning

confidence: 99%

Techno-economic and environmental analysis of community energy management for peak shaving

Cossutta

Pholboon

McKechnie

et al. 2022

Energy Conversion and Management

View full text Add to dashboard Cite

“…For example, the timeseries of photovoltaic power production at multiple sites is modeled as the signal on the graph [48][49][50]. The graph neural network and the long-and short-term memory recurrent neural network were combined into a spatio-temporal GNN model to analyze the temporal and spatial characteristics of the historical data of photovoltaic power stations [26,50,51]. However, when the prediction model is faced with the fluctuation of power generation, the fluctuation of the predicted value always lags behind that of the actual value.…”

Section: Introductionmentioning

confidence: 99%

Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN)

et al. 2023

View full text Add to dashboard Cite

The future power grid will have more distributed energy sources, and the widespread access of distributed energy sources has the potential to improve the energy efficiency, resilience, and sustainability of the system. However, distributed energy, mainly wind power generation and photovoltaic power generation, has the characteristics of intermittency and strong randomness, which will bring challenges to the safe operation of the power grid. Accurate prediction of solar power generation with high spatial and temporal resolution is very important for the normal operation of the power grid. In order to improve the accuracy of distributed photovoltaic power generation prediction, this paper proposes a new distributed photovoltaic power generation prediction model: ROLL-GNN, which is defined as a prediction model based on rolling prediction of the graph neural network. The ROLL-GNN uses the perspective of graph signal processing to model distributed generation production timeseries data as signals on graphs. In the model, the similarity of data is used to capture their spatio-temporal dependencies to achieve improved prediction accuracy.

show abstract

Short-Term Load Forecasting Using Soft Computing Techniques

Cited by 16 publications

References 11 publications

Factor Affecting Short Term Load Forecasting

Factor Affecting Short Term Load Forecasting

Techno-economic and environmental analysis of community energy management for peak shaving

Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN)

Contact Info

Product

Resources

About