On-Line Voltage Instability Prediction using an Artificial Neural Network

Hagmar, Hannes; Tuấn, Lê Anh; Carlsot, Ola; Eriksson, Robert

doi:10.1109/ptc.2019.8810808

Cited by 5 publications

(4 citation statements)

References 21 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As time progresses and if new events occur in the system, the network updates the assessment continuously. The network is also adapted to be able to indicate where in the system instability emerges, following the approach developed in [15], allowing more cost-effective countermeasures.…”

Section: Methodsmentioning

confidence: 99%

“…A method based on support vector machines (SVM) was proposed in [13], where generators' predicted reactive power output was used as an indicator for voltage collapse. A method based on training a NN to online monitor voltage security was proposed in [14], and in [15], a NN was used to also indicate where in the system instability would emerge.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Voltage Instability Prediction Using a Deep Recurrent Neural Network

Hagmar

Tong

Eriksson

et al. 2021

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

This paper develops a new method for voltage instability prediction using a recurrent neural network with long short-term memory. The method is aimed to be used as a supplementary warning system for system operators, capable of assessing whether the current state will cause voltage instability issues several minutes into the future. The proposed method uses a long sequence-based network, where both real-time and historic data are used to enhance the classification accuracy. The network is trained and tested on the Nordic32 test system, where combinations of different operating conditions and contingency scenarios are generated using time-domain simulations. The method shows that almost all N-1 contingency test cases were predicted correctly, and N-1-1 contingency test cases were predicted with over 95 % accuracy only seconds after a disturbance. Further, the impact of sequence length is examined, showing that the proposed long sequenced-based method provides significantly better classification accuracy than both a feedforward neural network and a network using a shorter sequence.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Voltage Instability Prediction Using a Deep Recurrent Neural Network

Hagmar

Tong

Eriksson

et al. 2021

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of AI is introduced to solve the optimum values of a system or condition particularly in the fields of economic dispatch, capacitor placement and sizing, and assessment and improvement of voltage and oscillatory stability. Artificial neural networks [16,17], evolutionary programming (EP) [18][19][20], artificial immune systems (AIS) [21][22][23], and ant colony optimization (ACO) [24][25][26] are AI approaches that are commonly used in power systems. The EP algorithm is modeled on the biological evolution process of solving a complex problem.…”

mentioning

confidence: 99%

PSO-Based Oscillatory Stability Assessment by Using the Torque Coefficients for SMIB

et al. 2020

View full text Add to dashboard Cite

This study discusses the evaluation of oscillatory stability based on the synchronizing K s and damping K d torque coefficients for a single-machine system connected to an infinite bus (SMIB). Particle swarm optimization (PSO) technique is used to determine K s and K d values and subsequently identify the oscillatory stability conditions in the SMIB. The ability of PSO is compared with those of evolutionary programming (EP) techniques and artificial immune system (AIS). The least square (LS) method is selected as the benchmark for K s and K d values determined by PSO, EP, and AIS. Simulation results show that PSO successfully estimated K s and K d values closest to LS compared with EP and AIS. PSO also uses lower computational time compared with those of the two other techniques. The proposed technique is suitable for solving oscillatory stability problems based on the determination of eigenvalues and minimum damping ratio.Energies 2020, 13, 1231 2 of 15 K d values. Thus, heuristic techniques are introduced to solve this problem. K s and K d values will be optimized from the beginning of the data until constant K s and K d values are obtained. Therefore, only a portion of the data is necessary for estimating K s and K d . Minor data errors do not significantly affect the determination of K s and K d values.In recent years, the use of artificial intelligence (AI) technology has become the preferred option in solving power system problems. The use of AI is introduced to solve the optimum values of a system or condition particularly in the fields of economic dispatch, capacitor placement and sizing, and assessment and improvement of voltage and oscillatory stability. Artificial neural networks [16,17], evolutionary programming (EP) [18][19][20], artificial immune systems (AIS) [21][22][23], and ant colony optimization (ACO) [24][25][26] are AI approaches that are commonly used in power systems. The EP algorithm is modeled on the biological evolution process of solving a complex problem. The main features of EP include the mutation process of the next generation and the selection of increasingly powerful genes. The AIS algorithm uses a concept similar to that of EP. Although both concepts are biologically based on living things, EP focuses on the evolution of living things, whereas AIS adopts the concept of the living immune system. The difference between AIS and EP algorithms is that AIS has an additional process of cloning called the clonal selection algorithm. However, the ACO approach is inspired by the true behavior of ants while searching for food and interacting with fellow ants. In ACO, artificial ants (the search agent) will communicate by using pheromones, which guide the searcher ants to solve the calculation problem by tracking the best route. Meanwhile, the particle swarm optimization (PSO) [27][28][29][30] concept mimics the movements of a herd, such as the behavior of schooling fish and swarming insects. This technique was originally founded based on the population of random particles, in which every p...

show abstract

“…Os autores em (ASHRAF et al, 2017;LI;AJJARAPU, 2017;HAGMAR et al, 2019;ZHOU;ANNAKKAGE;RAJAPAKSE, 2010) propõem utilizar diferentes redes neurais para estimar a margem de estabilidade de tensão de sistemas elétricos. Tais abordagens dependem de um banco de dados das possíveis condições de operação do sistema para estimar a margem de estabilidade do sistema para a etapa de treinamento e definição dos pesos da rede neural.…”

Section: Introductionunclassified

Método rápido para análise da segurança dinâmica de sistemas de potência considerando estabilidade a pequenas perturbações e de tensão

Bento¹

View full text Add to dashboard Cite

MET) é medida como sendo a diferença entre o ponto de máximo carregamento (nariz da curva PV e definida como Bifurcação Sela-Nó (BSN)) numa dada direção de crescimento de carga e o carregamento atual. Entretanto, esta margem pode não refletir adequadamente os verdadeiros limites de carregamento do sistema quando não se consideram instabilidades oscilatórias devido a Bifurcação de Hopf (BH) (perda da Estabilidade a Pequenas Perturbações). Isto ocorre sempre que estes estudos são realizados em modelos estáticos simplificados que não exibem este tipo de mecanismo de instabilidade. Deste modo, estudos considerando apenas a modelagem estática simplificada na análise da Estabilidade de Tensão (ET), apesar de serem adequados para uma parcela de problemas que podem existir em um SEP, não são aplicáveis a outra parcela significativa desse conjunto de fenômenos. Portanto, tendo em vista esta argumentação, esta pesquisa de doutorado propõe inovações nos estudos relacionados a estabilidade de um SEP, a partir de dois aspectos. Para tal um dos objetivos desta pesquisa é avaliar conjuntamente as Margens de Estabilidade de Tensão e a Pequenas Perturbações de um SEP, a partir do desenvolvimento de um procedimento unificado. Em outras palavras, a proposta é de desenvolver um método que consiga calcular uma única margem de estabilidade que já contemple BSN e BH na região de segurança dinâmica. Além disso, informações de grandezas elétricas fornecidas por Unidades de Medição Fasorial de barras selecionadas do sistema permitirão monitorar o SEP e fornecer indicativos de adequação na estimativa atual da margem de segurança citada para a atual direção de crescimento de carga. Caso seja identificada uma violação, a direção de crescimento de carga deve ser atualizada para o novo cenário do sistema de potência e uma nova margem de segurança deve ser obtida. Desenvolver um procedimento de monitoramento da adequação da margem de estabilidade bem como um procedimento de atualização da direção de crescimento de carga também são objetivos da pesquisa de doutorado. Estas informações irão indicar a necessidade de recalcular tal margem para um novo cenário de operação.

show abstract

On-Line Voltage Instability Prediction using an Artificial Neural Network

Cited by 5 publications

References 21 publications

Voltage Instability Prediction Using a Deep Recurrent Neural Network

Voltage Instability Prediction Using a Deep Recurrent Neural Network

PSO-Based Oscillatory Stability Assessment by Using the Torque Coefficients for SMIB

Método rápido para análise da segurança dinâmica de sistemas de potência considerando estabilidade a pequenas perturbações e de tensão

Contact Info

Product

Resources

About