>2007 0.3669 3669
Where PRPSR stands for the processed predicted solar
radiation; PRSR stands for the predicted solar radiation,
MJ/m2.
The trend of the solar radiation variations of Guangzhou is
shown in Figure 5.
Solar radiation
Predicted solar radiation
1962 1964 1966 1968 1970 1972 1974 1976 1978 1980 1982 1984 1986 1988 1990 1992 1994 1996 1998 2000 2002 2004 2006 2008 2010
3000
3200
3400
3600
3800
4000
4200
4400
4600
4800
5000
5200
5400
5600
5800
x
y solar radiation (MJ/m2)
year
Figure 5. The trend of yearly total solar radiation variations of
Guangzhou
As shown in Figure 6, there is a decline of yearly solar
radiation of Guangzhou from 1960s to 2000s, with some
fluctuations. At the year 1995, the solar radiation reaches its
minimum value, from then on, the yearly solar radiation
begins to increase. It is predicted by the prediction results that
the solar radiation of Guangzhou will continue to be larger
from the year 1995, with some fluctuations.
V. CONCLUSIONS
A BP neutral network for the yearly solar radiation of
Guangzhou is proposed in this paper by using the real
radiation data to train the network and the results shows that
the predicted data is similar to the real data in a large scale,
with minor errors. It is proved by the calculating results that
the learning method is very effective in determining the solar
radiations and trains the neutral network. Solar radiation data
of Guangzhou from the year 2004-2010 are properly
predicted and the results show that there will be larger
fluctuations in the following years. As to the design of
photovoltaic system, the designer can use the predicted data
for reference rather than the historical data. Since the value of
the yearly solar radiation varies every year and it shows a
strong regularity, using predicted data will make better reflect
the real solar radiation status in the following years thus will
be more precise.
REFERENCES
[1] Zhou Jin, Wu Yezheng, Yan Gang & Ma Zhenjun, “Solar radiation
estimation using artificial neutral networks”, Acta Energiae Solaris
Sinica. Vol. 26, No. 4, 2005:509-512
[2] Cao Shuanghua, Cao Jiacong, “Study of Chaos optimization neutral
networks for the forecast of hourly solar irradiation”, Acta Energiae
Solaris Sinica. Vol. 27, No. 2, 2006:164-169.
[3] Ren M J, Wright J A, “Adaptive dismal prediction of ambient dry-bulb
temperature and solar radiation”, HVAC and R Research, Vol. 8, No. 4,
2002: 383-401.
[4] Parishward G V, Bhardwaj R K, Nema V K, “Estimation of hourly
solar radiation for India”, Renewable Energy, Vol. 12, No. 3, 1997:
303-313.
[5] Muneer T, Gul M, Kambezedis H, “Evaluation of an all-sky
meteorological radiation model against long-term measured hourly
data” Energy Conversion Management, Vol. 39, No. 3, 1998: 303-307.
[6] Raja I A, “Insulation sunshine relation with sunshine and latitude”,
Solar Energy, Vol. 53, No. 1, 1994: 161-168.
[7] Supit I, Van Kappel R R, “A simple method to estimate global
radiation”, Solar Energy, Vol. 63, 1998:147.
[8] Sin-Chun Ng, Chi-Chuang Cheung & Shu-Hung Leung, “Magnified
gradient function with deterministic weight modification in adaptive
learning”, IEEE Transactions on Neutral Networks, Vol. 15, No. 6,
2004: 1411-1423.
[9] Li Ping, Zeng Lingke & Shui Anze, “Des
本论文由英语论文网提供整理,提供论文代写,英语论文代写,代写论文,代写英语论文,代写留学生论文,代写英文论文,留学生论文代写相关核心关键词搜索。