Linearizing Power Flow Model: A Hybrid Physical Model-Driven and Data-Driven Approach

The data warehouse design is currently recognized as the most important and complicated phase in any project of decision support system implementation. Its complexity is primarily due to the proliferation of data source types and the lack of a standardized and well-structured method, hence the increasing interest from researchers who have tried to develop new methods for the automation and standardization of this critical stage of the project. In this paper, the authors present the set of developed methods that follows the data-driven paradigm, and they propose a new data-driven method called X-ETL. This method aims to automating the data warehouse design by generating star models from relational data. This method is mainly based on a set of rules derived from the related works, the Model-Driven Architecture (MDA) and the XML language.

Download Full-text

Using Integration of Thermal-Balance Based and Data-Driven Models to Determine Single Duct Variable Air Volume System Cooling Baseline

ASME 2013 7th International Conference on Energy Sustainability ◽

10.1115/es2013-18402 ◽

2013 ◽

Author(s):

Gyujin Shim ◽

Li Song ◽

Gang Wang

Keyword(s):

Physical Model ◽

Least Square Method ◽

Energy Performance ◽

Least Square ◽

Physical Models ◽

Data Driven ◽

Lumped Model ◽

Variable Air Volume ◽

Data Driven Approach ◽

Cooling Coil

In order to use real-time energy measurements to identify system operation faults and inefficiencies, a cooling coil energy baseline is studied in an air-handling unit (AHU) through an integration of physical models and a data driven approach in this paper. A physical model for an AHU cooling coil energy consumption is first built to understand equipment mechanism and to determine the variables impacting cooling coil energy performance, and then the physical model is simplified into a lumped model by reducing the number of independent variables needed. Regression coefficients in the lumped model are determined statistically through searching optimal fit using the least square method with short periods of measured data. Experimental results on an operational AHU (8 ton) are presented to validate the effectiveness of this approach with statistical analysis. As a result of this experiment, the proposed cooling energy baselines at the cooling coil have ±20% errors at 99.7% confidence. Six-day data for obtaining baseline is preferred since it shows similar results as 12-day.

Download Full-text

Uncertainty Propagation from the Cell Transmission Traffic Flow Model to Emission Predictions: A Data-Driven Approach

Transportation Science ◽

10.1287/trsc.2017.0787 ◽

2018 ◽

Vol 52 (6) ◽

pp. 1327-1346

Author(s):

Arwa S. Sayegh ◽

Richard D. Connors ◽

James E. Tate

Keyword(s):

Traffic Flow ◽

Flow Model ◽

Uncertainty Propagation ◽

Data Driven ◽

Traffic Flow Model ◽

Cell Transmission ◽

Data Driven Approach

Download Full-text

Fast Heuristic AC Power Flow Analysis with Data-Driven Enhanced Linearized Model

Energies ◽

10.3390/en13133308 ◽

2020 ◽

Vol 13 (13) ◽

pp. 3308

Author(s):

Xingpeng Li

Keyword(s):

Power Systems ◽

Power System ◽

Power Flow ◽

Flow Model ◽

Reactive Power ◽

Unit Commitment ◽

Flow Analysis ◽

Data Driven ◽

Dc Power ◽

Ac Power

Though the full AC power flow model can accurately represent the physical power system, the use of this model is limited in practice due to the computational complexity associated with its non-linear and non-convexity characteristics. For instance, the AC power flow model is not incorporated in the unit commitment model for practical power systems. Instead, an alternative linearized DC power flow model is widely used in today’s power system operational and planning tools. However, DC power flow model will be useless when reactive power and voltage magnitude are of concern. Therefore, a linearized AC (LAC) power flow model is needed to address this issue. This paper first introduces a traditional LAC model and then proposes an enhanced data-driven linearized AC (DLAC) model using the regression analysis technique. Numerical simulations conducted on the Tennessee Valley Authority (TVA) system demonstrate the performance and effectiveness of the proposed DLAC model.

Download Full-text

The application of machine learning to structural health monitoring

Philosophical Transactions of The Royal Society A Mathematical Physical and Engineering Sciences ◽

10.1098/rsta.2006.1938 ◽

2006 ◽

Vol 365 (1851) ◽

pp. 515-537 ◽

Cited By ~ 163

Author(s):

Keith Worden ◽

Graeme Manson

Keyword(s):

Machine Learning ◽

Normal Condition ◽

Damage Identification ◽

Measured Data ◽

Data Driven ◽

High Fidelity ◽

Element Analysis ◽

Model Driven ◽

Statistical Representation ◽

Data Driven Approach

In broad terms, there are two approaches to damage identification. Model-driven methods establish a high-fidelity physical model of the structure, usually by finite element analysis, and then establish a comparison metric between the model and the measured data from the real structure. If the model is for a system or structure in normal (i.e. undamaged) condition, any departures indicate that the structure has deviated from normal condition and damage is inferred. Data-driven approaches also establish a model, but this is usually a statistical representation of the system, e.g. a probability density function of the normal condition. Departures from normality are then signalled by measured data appearing in regions of very low density. The algorithms that have been developed over the years for data-driven approaches are mainly drawn from the discipline of pattern recognition, or more broadly, machine learning. The object of this paper is to illustrate the utility of the data-driven approach to damage identification by means of a number of case studies.

Download Full-text

A data-driven approach for constructing a zonal network model for long-term dispatch planning

10.31224/osf.io/cmfd6 ◽

2020 ◽

Author(s):

Phen Chiak See

Keyword(s):

Power Flow ◽

Western Europe ◽

Effective Means ◽

Data Driven ◽

Transmission Network ◽

Zonal Model ◽

Ex Post ◽

Data Driven Approach ◽

Generation Dispatch

The most important aspect of the planning of power generation dispatch is its complementary relationship with the power flows on the interconnectors of the transmission network. A plan could become invalid if the power flow created violates the transfer limit of any interconnectors. The long-term dispatch planning is more affected by this because of the relative difficulty in predicting the state of the transmission network in advance. It is generally planned in a trade-based manner, without a means to explicitly compute the power flows. Deviations in the plans are then corrected near the time of dispatch, in the expense of opportunity costs. In Europe, the flow-based market coupling is proposed in the Central Western Europe, which is an effective means for modeling the inter-zonal power flows and transfer capacity allocations. However, its usefulness for long-term planning is still limited. Especially, the Power Transfer Distribution Factors (PTDFs) of its model (key parameter for integrating power flow in dispatch planning) is stochastic and unpredictable. This paper introduces a data-driven approach to construct a zonal model for closing the gap between the long-term and the actual dispatch plan. It is able to reconstruct all zonal PTDFs existed in the system, by inverse modeling the ex-post power flow data. The paper as well presented the validity of decomposing a large zonal model into substantially smaller sub-problems, and the existence of clusters of ex-post power flow cases which share the same zonal PTDFs. These features have greatly simplified the implementation of the method.

Download Full-text

Distributionally Robust Stochastic Optimal Power Flow Considering N-1 Security Constraints with renewable

E3S Web of Conferences ◽

10.1051/e3sconf/202126102017 ◽

2021 ◽

Vol 261 ◽

pp. 02017

Author(s):

Shiyuan Ni ◽

Guilian Wu ◽

Zehao Wang ◽

Yi Lin ◽

Defei Yao ◽

...

Keyword(s):

Renewable Energy ◽

Power Flow ◽

Optimal Power Flow ◽

Flow Model ◽

Renewable Energy Sources ◽

Data Driven ◽

Stable Operation ◽

Optimal Power ◽

Distributionally Robust ◽

Constraint Model

This paper proposes a data-driven stochastic optimal power flow model considering the uncertainties of renewable energy sources. The proposed model also focuses on the constraints of reactive voltage, aiming at improving the safety of voltage amplitude and reactive power output at each bus. Using data-driven linearization techniques, we simplified the calculation of system. In addition, Wasserstein ambiguity set was used to describe the uncertainties of renewable energy prediction error distribution, and a robust stochastic optimal power flow model considering N-1 security constraints is established. The simulation results on IEEE-39 system showed the accuracy and effectiveness of the distributionally robust optimization model and the reactive voltage constraint model provided a more stable operation schedule.

Download Full-text