A Data-driven Dynamic Rating Forecast Method and Application for Power Transformer Long-term Planning
📝 Abstract
This paper presents a data-driven method for producing annual continuous dynamic rating of power transformers to serve the long-term planning purpose. Historically, research works on dynamic rating have been focused on real-time/near-future system operations. There has been a lack of research for long-term planning oriented applications. Currently, most utility companies still rely on static rating numbers when planning power transformers for the next few years. In response, this paper proposes a novel and comprehensive method to analyze the past 5-year temperature, loading and load composition data of existing power transformers in a planning region. Based on such data and the forecasted area load composition, a future power transformer loading profile can be constructed by using Gaussian Mixture Model. Then according to IEEE std. C57.91-2011, a power transformer thermal aging model can be established to incorporate future loading and temperature profiles. As a result, annual continuous dynamic rating profiles under different temperature scenarios can be determined. The profiles can reflect the long-term thermal overloading risk in a much more realistic and granular way, which can significantly improve the accuracy of power transformer planning. A real utility application example in Canada has been presented to demonstrate the practicality and usefulness of this method.
💡 Analysis
This paper presents a data-driven method for producing annual continuous dynamic rating of power transformers to serve the long-term planning purpose. Historically, research works on dynamic rating have been focused on real-time/near-future system operations. There has been a lack of research for long-term planning oriented applications. Currently, most utility companies still rely on static rating numbers when planning power transformers for the next few years. In response, this paper proposes a novel and comprehensive method to analyze the past 5-year temperature, loading and load composition data of existing power transformers in a planning region. Based on such data and the forecasted area load composition, a future power transformer loading profile can be constructed by using Gaussian Mixture Model. Then according to IEEE std. C57.91-2011, a power transformer thermal aging model can be established to incorporate future loading and temperature profiles. As a result, annual continuous dynamic rating profiles under different temperature scenarios can be determined. The profiles can reflect the long-term thermal overloading risk in a much more realistic and granular way, which can significantly improve the accuracy of power transformer planning. A real utility application example in Canada has been presented to demonstrate the practicality and usefulness of this method.
📄 Content
Abstract—This paper presents a data-driven method for
estimating annual continuous dynamic rating of power
transformers
to
serve
the
long-term
planning
purpose.
Historically, research works on dynamic rating have been
focused on real-time/near-future system operations. There has
been a lack of research for long-term planning oriented
applications. Currently, most utility companies still rely on static
rating numbers when planning power transformers for the next
few years. In response, this paper proposes a novel and
comprehensive method to analyze the past 5-year temperature,
loading
and
load
composition
data
of
existing
power
transformers in a planning region. Based on such data and the
forecasted area load composition, a future power transformer’s
load shape profile can be constructed by using Gaussian Mixture
Model. Then according to IEEE std. C57.91-2011, a power
transformer thermal aging model can be established to
incorporate future loading and temperature profiles. As a result,
annual continuous dynamic rating profiles under different
temperature scenarios can be determined. The profiles can
reflect the long-term thermal overloading risk in a much more
realistic and granular way, which can significantly improve the
accuracy of power transformer planning. A real utility
application example in Canada has been presented to validate
and demonstrate the practicality and usefulness of this method.
Index Terms—Dynamic Rating, Long-term System Planning,
Gaussian Mixture Model, Transformer Thermal Aging
I. INTRODUCTION
CCURATE long-term planning is the key to ensure
balanced cost and reliability of power system in the next
5-10 years. As a critical and costly component, power
transformer planning is an important part of long-term system
planning process, in which the forecasted area load to be
supplied by the transformer is compared with transformer’s
rating to determine the proper transformer sizing.
However, most utility companies currently use static power
transformer rating assumption, in many cases the nameplate
ratings for long-term system planning [1-4].These assumptions
can be overly conservative or inaccurate as they do not reflect
the dynamic temperature conditions in the planning region
throughout a year. This is especially true for relatively cold
areas such as Canada where the ambient temperatures are
relatively low. According to IEEE std. C57.91-2011, the
insulation deterioration of power transformers is a function of
M. Dong is with Department of System Planning and Asset Management, ENMAX Power Corporation, Calgary, AB, Canada, T2G 4S7 (e-mail: mingdong@ieee.org)
dynamic
loading
and
ambient
temperature.
Proper
combinations of dynamic loading and ambient temperature
could safely allow transformer loading to exceed the
nameplate rating without causing any damage. Therefore, to
improve the cost-effectiveness of planning decisions, a
scientific and realistic way to establish annual continuous
dynamic rating for power transformers is required.
Previously, research works on dynamic rating mainly
focused on real-time or near-future operations of system
equipment [5-9]. Based on the monitoring of electrical and
environmental conditions, real-time or near-future equipment
ratings can be estimated or predicted and flexible loading
operations or asset management decisions can be optimized
accordingly to capitalize on such varying ratings. The research
on establishing typical annual dynamic ratings to serve the
long-term planning purpose has not been found. For such
applications, there are two unique challenges:
- No monitoring data is available for long-term future. Since the purpose of planning is to study the future load growth of an area, both long-term loading and temperature profiles are currently unknown and have to be estimated. Also, due to the high uncertainties over a long-term planning horizon, different scenarios may need to be studied.
- Unlike operational dynamic rating which usually focuses
on a short period of time such as a few hours or a few days,
dynamic rating for long-term planning should be established
on an annual basis to cover different seasons.
To tackle the above challenges, this paper proposes a novel
and comprehensive data analytics method as shown in Fig.1.
Each step in the flowchart is explained as follows:
Step 1: The past 5-year hourly temperature data in the
planning region is analyzed to establish three long-term
annual temperature profiles under three scenarios;
Step 2: For each future day in the 365-day profile, 5 historical days that have closest temperature and calendar characteristics are found;
Step 3: Within these 5 days, the relationships between the existing transformers’ load compositions and the future transformer’s forecasted load composition are analyzed by using Gaussian Mixture
This content is AI-processed based on ArXiv data.