IEEE Power & Energy Magazine - May/June 2018 - 65
of data generated from power systems depends on both the
management model and the applications of advanced techniques such as blockchain. industrial and academic researchers should make greater efforts in this area.
traditional synchronous generator-dominated power systems.
analyzing and evaluating the stability of a power system from
a data-driven perspective offer new opportunities and also
Deregulation of the Electric Power Industry
the power industry is experiencing a fast transition of market deregulation, especially on the demand side. various participants such as retailers and aggregators will be introduced,
and new business models will emerge. in a more competitive
environment, deregulated retailers and aggregators have more
incentive to provide value-added services to maximize their
profits. big data analytics will be more widely applied by participators in the power market, which is not limited to power
grid companies, to uncover massive and valuable information
from smart-meter data. for example, in guangdong province,
electricity retailers are required to provide accurate demand
forecasts. forecasting errors that exceed 3% will be penalized. in this situation, retailers or aggregators benefit from
making full use of various data that improve the accuracy of
their forecasting model.
the retail electricity market is still at its initial stage in china.
new business models will change the electricity behaviors
of consumers and further alter the way the power system is
operated. for example, traditional load and price forecasting methods may not be effective in a transactive energy
framework. big data analytics is able to provide an effective way to understand the behavior of the power system and
the mechanisms behind it in such changing environments.
furthermore, data-driven forecast optimization and control
methods should be developed to support the operation of the
power system from both the reliability and business points of
view, e.g., how to encourage interaction between consumers
and power grids and how to provide personalized services.
china's electric power industry has witnessed unprecedented
development in big data analytics and applications since
2013, from the germination of the big data concept to academic research and then to industrial applications. however,
many more and much greater challenges will emerge in the
future. big data analytics and applications in the electric
power industry must continue to move forward.
High Share of Renewable Energy Integration
the chinese government set an aggressive goal to develop
renewable energy, especially in the power industry. the high
penetration of renewable energy integration has brought
great challenges to the traditional power system. big data
analytics is able to contribute to solving these problems. for
example, the integration of distributed renewable energy
presents difficulties to net load forecasting. Making decisions concerning how to model and quantify the introduced
uncertainties and consider these uncertainties in power system planning and operation is imperative. big data technologies can provide a deeper understanding of the complex
impact of uncertainty and intermittency on the power system. these technologies also offer a promising means to
tackle such problems by introducing data-driven optimization models for power system planning and operation.
with a high share of renewable energy integration, traditional power systems may transform into power electronicsdominated power systems, the stability mechanism of which
will fundamentally change and is much more complex than
this work was supported in part by the national Key r&D
Program of china (2016yfb0900100), the Key Project of
national natural science fund (61533010, 51437003), and
the national high-tech research Program (2015aa050204).
we thank Prof. youyuan wang from chongqing university
and Prof. Jun an from northeast electric Power university
for their input.
For Further Reading
X. yu and y. Xue, "smart grids: a cyber-physical systems perspective," in Proc. IEEE, vol. 104, no. 5, pp. 1058-1070, 2016.
y. wang, Q. chen, c. Kang, and Q. Xia, "clustering of
electricity consumption behavior dynamics toward big data
applications," IEEE Trans. Smart Grid, vol. 7, no. 5, pp.
n. Zhang, c. Kang, D. s. Kirschen, Q. Xia, w. Xi, J. hunag, and Q. Zhang, "Planning pumped storage capacity for
wind power integration," IEEE Trans. Sustainable Energy,
vol. 4, no. 2, pp. 393-401, 2013.
r. J. Liao, J. P. bian, L. J. yang, s. grzybowski, y.
y. wang, and J. Li, "forecasting dissolved gases content in
power transformer oil based on weakening buffer operator
and least square support vector machine-Markov," IET Gener. Transm. Distrib., vol. 6, no. 2, pp. 142-151, 2012.
b. Xiao, P. guo, g. Mu, g. yan, P. Li, h. cheng, J. Li, and
y. bai, "a spatial load forecasting method based on the theory of clustering analysis," Phys. Procedia, vol. 24, part a,
pp. 176-183, 2012. doi 10.1016/j.phpro.2012.02.027.
Chongqing Kang is with tsinghua university, beijing, china.
Yi Wang is with tsinghua university, beijing, china.
Yusheng Xue is with the state grid electric Power research institute, nanjing, china.
Gang Mu is with northeast electric Power university,
Ruijin Liao is with chongqing university, chongqing,
ieee power & energy magazine