Influenced by light, temperature, atmospheric pressure, and some other random factors, photovoltaic power has characteristics of volatility and intermittent. Accurately forecasting photovoltaic power can effectively improve security and stability of power grid system. The paper comprehensively analyzes influence of light intensity, day type, temperature, and season on photovoltaic power. According to the proposed scene simulation knowledge mining (SSKM) technique, the influencing factors are clustered and fused into prediction model. Combining adaptive algorithm with neural network, adaptive neural network prediction model is established. Actual numerical example verifies the effectiveness and applicability of the proposed photovoltaic power prediction model based on scene simulation knowledge mining and adaptive neural network.
Facing the increasingly severe problem of tradition energy consumption and environment pollution, solar power is attracting more and more attention. With the development of grid-connected photovoltaic power (PV) generation, it has been regarded as a kind of effective way to make full use of solar energy, which is economic and environmental [
In the early period, trend extrapolation, regression analysis, time series [
This paper is organized as follows. In Section
Many factors influence the generating capacity of PV grid system. Actually, because of various conditions, it could not be determined in advance one by one and is not necessary to be distinguished meticulously. Some influences can be combined into several correction groups, added with certain safety coefficient.
Influenced by many factors, change of PV generation capacity is a nonstationary random process with obvious cyclicity. An obvious feature for PV system is that the output time series is highly autocorrelated. Almost all PV grid inverters run with a relatively stable power conversion efficiency at maximum power point tracking (MPPT) model. Its output power is highly correlated. Although the efficiency of power conversion and photoelectric conversion changes over time, during system life cycle, the variation is relatively small, so much so that in short-term prediction can be considered as constant.
Therefore, the power conversion efficiency of inverter, photoelectric conversion efficiency of PV array, and area of the PV array can be ignored, since they are implicitly included in electricity data. Based on the above analysis, light intensity, day type, temperature, season, and the output data are the major factors taken into consideration in this paper.
A method of calculating output power per unit area can be found in [
Photovoltaic generation power and light intensity.
Generally, PV system mainly outputs power from 7:00 to 18:00. Figure
Photovoltaic power on different day types.
For sunny day type, changes of electricity curves can broadly reflect the intensity of sun irradiation in a day. When the weather becomes rainy, solar irradiation intensity decreases obviously. If the input parameters ignore these changes of radiation intensity, the forecast will be inaccurate. So, some appropriate variables to reflect weather change correctly as well as corresponding variation of PV are needed.
With the development of weather forecast, the prediction model ought to take daily weather forecast information into consideration to deal with different day types. But, weather parameters are generally given by vague description, such as sunny, cloudy, rain, moderate rain, or heavy rain. So, plenty of statistical analyses on historical electricity have to be done to decide how to change vague and uncertain description of day types to accurate information, which is accepted by prediction model. Thus, In order to improve the prediction accuracy, PV data needs to be classified into three groups: sunny, cloudy, and rainy.
The changes of atmospheric temperature can influence photovoltaic power system to a certain degree. Though historic data of photovoltaic reflects similarity between power curve and day types, the changes of temperature can reflect tiny change of curve height in the same day. So, we should take atmospheric temperature as an input variable.
Figure
Influence of temperature on photovoltaic power.
Season also plays an important role in photovoltaic output. The output of photovoltaic modules is changing with solar radiation intensity, and solar radiation intensity is different in diverse seasons.
Besides, the photovoltaic system is installed in different locations where the climatic condition is variable, which make the effect degree of season on photovoltaic output the different. According to NASA, we can get atmosphere data of diverse districts. The data reflects that temperature and solar radiation intensity vary a lot in different months. Especially in summer, the numerical values of temperature and solar radiation are much higher than that in winter. So, we can infer that the output of photovoltaic system varies in variable seasons.
Based on the above analysis, we make statistics choosing electric production data from June to August of 2010 and from December 2010 to February 2011. We aggregate data of two to three months and make comparison in accordance with day arrays. In Figure
Photovoltaic generation power in different season.
This section mainly analyzes several influential factors aimed at the uncertainty of photovoltaic output, including day type, season, temperature, and solar radiation. Through the comparison and analysis of historic data, we can approximately know their effect on the photovoltaic output. In the following section, we will build an accurate and reasonable forecast model based on the results above.
For photovoltaic power, we mainly consider the influence of light intensity, season, day type, and temperature. According to scene simulation knowledge mining, select high similarity historical data and meteorological environment as learning sample to complete scene simulation knowledge mining as the first step. Neural network prediction model can simulate arbitrary complex nonlinear mapping with the advantage of being intelligent. Here adaptive neural network is chosen to forecast photovoltaic power.
By the above analysis, we know that the influence degree of meteorological factors on photovoltaic power is different. Light intensity, day type, temperature, and season can make different degrees of influence on photovoltaic power, and the power is often a result of combined action of various meteorological factors [
According to scene simulation knowledge mining technique, take the day characteristic similarity and the former trend similarity as index to choose similar scene as input value of forecast model.
Characteristic similarity for two days
Former trend similarity of
Former trend similarity refers to average
According to the latest situation to automatically adjust model so as to achieve satisfied prediction effect which is very important, adaptive prediction method continuously automatically adjusts model structure and parameters based on prediction deviation which actually forms a closed loop feedback [
Block diagram of an adaptive system.
According to model and actual value of
Works of the literature [
Adaptive artificial neural network.
The output of Figure
Adaptive neural network adopts the minimum mean square error (MSE) learning rule, namely, Windrow Hoff (WH) algorithm, to adjust weights and thresholds. For a given
Setting type (
Adaptive neural network is able to obtain a set of continuous data, make accurate predictions, automatically discard old data, and study new data in the process of learning [
The adaptive data training process is as follows [ Define the error function as
Set studied weight and threshold values as initial values of new training array’s weight and threshold, the new training function is
Start new forecast based on the studied weight in step
This power output prediction model of PV power generation system uses Mat lab programming implementation and selects Guangdong photovoltaic power generation system as an example. The precision time is 1 h, the time from 7:00 to 18:00. The sun radiation from 7 p.m. to 6 a.m. is 0, so it is not included in the study [
In order to validate the proposed prediction model, one day was randomly chosen from each season of the year 2010, that is, D1 = December 25 for winter, D2 = April 20 for spring, D3 = July 15 for summer, and D4 = October 23 for fall. Three models are chosen to be predicted, respectively. Model 1 is traditional BP neural network forecasting model without the proposed scene simulation knowledge mining. Model 2 is ordinary adaptive neural network forecasting model. Model 3 is the proposed adaptive neural network prediction model based on scene simulation knowledge mining. The following table is PV power prediction error from different prediction models. As can be seen from Table
Prediction error for different models.
Time | Winter | Spring | Summer | Fall | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
BP | NP | MODEL | BP | NP | MODEL | BP | NP | MODEL | BP | NP | MODEL | |
7 | — | — | — | 120.5 | 85.4 | 45.3 | 50.3 | 47.1 | 15.4 | 142.3 | 46.2 | 18.1 |
8 | 36.2 | 40.5 | 20.4 | 51.5 | 34 | 10.3 | 46.1 | 40.5 | 5 | 60.4 | 40 | 9.4 |
9 | 36 | 24 | 12.3 | 20.3 | 25 | 12.5 | 30.8 | 21.5 | 4 | 30.4 | 32.6 | 14.5 |
10 | 16.4 | 13.4 | 10.8 | 42.6 | 16 | 12.4 | 22.7 | 20.5 | 2.4 | 35.4 | 23.4 | 14.2 |
11 | 41.8 | 20.4 | 16.7 | 34.8 | 26.4 | 10.8 | 16.8 | 20.4 | 3.5 | 28.6 | 25 | 10.4 |
12 | 69 | 26.4 | 25.7 | 60.7 | 21.4 | 5.6 | 20.7 | 10.6 | 1.6 | 52 | 20.8 | 8.6 |
13 | 157.8 | 34.6 | 17.3 | 20.4 | 13.8 | 20.4 | 18.6 | 11.5 | 1.2 | 18.2 | 19.3 | 15.4 |
14 | 27.5 | 30.7 | 15 | 38.6 | 11.7 | 26.7 | 17.3 | 9.7 | 1 | 35.4 | 15.7 | 21.6 |
15 | 98.4 | 50.4 | 24.6 | 79.1 | 25.9 | 22.4 | 12.4 | 8.6 | 1.3 | 60.7 | 22.3 | 20 |
16 | 39 | 20 | 10.4 | 25.7 | 20.8 | 17.3 | 19.4 | 10.5 | 2.4 | 20.7 | 15.8 | 11.8 |
17 | 32.4 | 30 | 8.4 | 20 | 15.3 | 10.8 | 20.6 | 15.4 | 4.1 | 13 | 14 | 14 |
18 | 35.4 | 20.9 | 6.7 | 31 | 10.8 | 5.4 | 21.7 | 9.4 | 5.4 | 27.6 | 12.6 | 12.8 |
| ||||||||||||
Average | 53.6 | 28.3 | 15.3 | 45.4 | 25.5 | 16.7 | 24.8 | 18.8 | 3.9 | 43.7 | 24.0 | 14.2 |
In order to further assess the forecasting capability of the proposed adaptive neural network prediction model based on scene simulation knowledge mining, simulations are carried out for three different days—sunny day (SD), cloudy day (CD), and rainy day (RD) from each season, and the results obtained from the proposed model are presented in Table
Prediction error for different day styles.
Time | Winter | Spring | Summer | Fall | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Rainy day | Cloudy day | Sunny day | Rainy day | Cloudy day | Sunny day | Rainy day | Cloudy day | Sunny day | Rainy day | Cloudy day | Sunny day | |
7 | — | — | — | 52.4 | 34 | 20.4 | 30.4 | 22 | 15.4 | 35.4 | 20 | 10.5 |
8 | 36.2 | 20.5 | 12.5 | 30.4 | 25.1 | 11 | 24.5 | 15.4 | 0.5 | 23.4 | 21.4 | 2.4 |
9 | 36 | 24 | 12.7 | 32.4 | 23 | 12.3 | 11.5 | 16.4 | 0.8 | 31.4 | 22 | 4.6 |
10 | 37.6 | 23.7 | 10.4 | 35 | 21 | 10.4 | 20.4 | 12 | 2.1 | 30 | 21.4 | 0.8 |
11 | 41.8 | 20.7 | 16.5 | 34.8 | 26.4 | 14 | 15.3 | 10.5 | 1.5 | 28.6 | 20.1 | 10.5 |
12 | 30.5 | 26.4 | 15.4 | 30.4 | 22.4 | 10.5 | 12.5 | 13 | 1.4 | 27.5 | 15.2 | 5.4 |
13 | 25.4 | 24.5 | 18.4 | 31.2 | 15.4 | 11.4 | 10.5 | 5.6 | 1.6 | 30.4 | 10.5 | 12 |
14 | 27.5 | 20.1 | 12 | 24.3 | 13.4 | 5.4 | 25.6 | 8.4 | 2.4 | 25 | 5.4 | 4.5 |
15 | 35.1 | 23.5 | 11 | 38.1 | 20.7 | 8.6 | 24.1 | 8.6 | 1.8 | 34 | 15.4 | 16.4 |
16 | 39 | 24 | 10.3 | 25.7 | 22 | 7.1 | 29.5 | 10.7 | 0.7 | 29 | 18.6 | 11.4 |
17 | 32.8 | 22 | 11.7 | 30.4 | 15.3 | 10.8 | 26.4 | 11 | 1.4 | 27 | 14.2 | 10.5 |
18 | 33.4 | 20.4 | 6.7 | 30 | 14.5 | 6.3 | 22.7 | 13 | 1.8 | 34.5 | 10.4 | 2.4 |
| ||||||||||||
Average | 34.1 | 22.7 | 12.5 | 32.9 | 21.1 | 10.7 | 21.1 | 12.2 | 2.6 | 29.7 | 16.2 | 7.6 |
Through the effective analysis of influencing factors of PV power output, combined with the improved adaptive neural network prediction model and scene simulation knowledge mining technique, a photovoltaic power prediction model based on scene simulation knowledge mining and adaptive neural network is proposed. The benefit of the proposed approach is that it does not require complex modeling and complicated calculation; forecast under different weather types can be carried out using only historical power data and weather data. The test results proved validity and accuracy of the proposed approach; the proposed approach can be used to forecast the power output of photovoltaic system precisely.
With the development of the grid-connected photovoltaic power (PV), it has been regarded as a kind of effective way to make full use of solar energy, which is economic and environmental. Influenced by light, temperature, atmospheric pressure, and some other random factors, photovoltaic power has characteristics of volatility and intermittece. Accurately forecasting photovoltaic power can effectively improve security and stability of power grid system. We comprehensively analyze the influence of light intensity, day type, temperature, and season on photovoltaic power in this paper. According to proposed scene simulation knowledge mining technique, similar meteorological factors and power are taken as input value in prediction model. Combining advanced adaptive neural network and scene simulation knowledge mining, photovoltaic power prediction model based on scene simulation knowledge mining and adaptive neural network is established. Guangdong photovoltaic power generation system is selected to verify the proposed model. The test results proved validity and accuracy of the proposed approach; the proposed approach can be used to forecast the power output of photovoltaic system precisely.
This work was partially supported by the Natural Science Foundation of China (71071052) and the Fundamental Research Funds for the Central Universities (12QX22).