Bad data detection and handling in distribution grid state estimation using artificial neural networks

Cramer, Moritz; Goergens, Philipp; Schnettler, Armin

doi:10.1109/ptc.2015.7232655

Cited by 19 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is partly due to space limitations but also because the optimization models that are the focus of this article are rarely applied to these sub-problems, especially in DSSE. Examples in the literature often resort to heuristic models, like in (Cramer et al, 2015;Gastoni et al, 2003), which use artificial neural networks and genetic algorithms, respectively.…”

Section: State Estimationmentioning

confidence: 99%

Applications of optimization models for electricity distribution networks

Claeys

Vanin

Geth

2021

WIREs Energy & Environment

View full text Add to dashboard Cite

Increased penetration of low‐carbon technologies, such as residential photovoltaic systems, electric vehicles, and batteries, can potentially cause voltage quality issues in distribution networks. Active distribution networks adopt control schemes where these assets are actively managed to prevent potential issues, increasing the network utilization. Mathematical optimization is a key technology in enabling such applications, either directly as the underlying solution, or for benchmarking effectiveness. As networks are operated closer to their engineering limits, models representing distribution network physics become increasingly important. This article reviews how distribution networks are modeled with varying degrees of detail in the context of optimization problems. It goes on to catalog the applications that use such models, and ends with an overview of toolchains to implement them, to enable the transition from the passive to active management of the distribution system. This article is categorized under: Energy Systems Analysis > Systems and Infrastructure

show abstract

Section: State Estimationmentioning

confidence: 99%

Applications of optimization models for electricity distribution networks

Claeys

Vanin

Geth

2021

WIREs Energy & Environment

View full text Add to dashboard Cite

show abstract

“…Negative measurement errors have impacts on the SE outcomes, making a must for BDDI and handling system which is an error correction method developed and tested with respect to the impact on the estimation of the system state for the distribution grid (DG). The DSSE provides insufficient real-time measurement data making the SE state changes from an overdetermined to an underdetermined system [7].…”

Section: Bad Data Detection Identification (Bddi) and Related Limitationsmentioning

confidence: 99%

“…The method has proven to be responsive towards uncorrected measurement errors and able to detect and accurately recognize single and multiple measurement error values. The proportion of varying DGSE performance is considerably minimized as well as the mean square error of the estimated system state is also lessened to a fraction by implementing the error correction process [7].…”

Section: Alternative Formulation Of Bddimentioning

confidence: 99%

“…Since these incorrect measurement values conflictingly impact the SE results, a system for bad data detection, identification (BDDI), and handling, i.e. correcting the detected error, is required which presents the issues or limitations available in the BDDI area and the available alternative formulation that has been implemented by researchers [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Power System State Estimation Bad Data Detection and Identification: A Review on Issues and Alternative Formulations

Gulcharan

Nor

Ibrahim

et al. 2017

IJEECS

View full text Add to dashboard Cite

State Estimation (SE) is the main function of power system where Energy Management System (EMS) is obliged to estimate the available states. Power system is a quasi-static system and hence changes slowly with time. Dynamic State Estimation (DSE) technique represents the time deviation nature of the system, which allows the forecasting of state vector in advance. Various techniques for DSE are available in the literature. This paper presents a review on different methodologies and developments in DSE, based on comprehensive survey of the available literature. From the survey it can be concluded that there are still areas in the developing DSE that can still be improved in terms of system computational time, redundancy and robustness of the system.

show abstract

“…Typical examples of KB methods are artificial neural networks (ANNs), support vector machines (SVMs), fuzzy logic, genetic algorithm etc. Among KB methods, ANN is the most common method used in power systems in the areas of event detection [11], fault location identification (FLI) [12], bad data detection, and distribution management [13]. ANN and SVM are combined to locate different types of faults in radial DN utilising measurements at substations, relays, and circuit breakers [14].…”

Section: Introductionmentioning

confidence: 99%