Search

The widespread adoption of photovoltaic (PV) systems results in reverse power flows that are already causing overvoltage problems in many distribution networks. To mitigate these voltage problems, distribution companies are using different voltage regulation approaches that exploit the flexibility of existing devices, such as on-load tap changers (OLTC) at primary substations, and the PV inverters themselves. However, the real-time process that determines the most adequate settings becomes more complex with the increasing number of devices that need to be controlled. This work presents a voltage regulation approach that uses the Machine Learning technique called Double Dueling Q-learning (DDQN) as an extremely fast alternative to coordinate the OLTC-fitted transformer at primary substations and the power factor of PV inverters. The proposed voltage regulation approach is assessed using a real Brazilian MV/LV feeder with 108 residential customers and 15 industrial/commercial customers, in which 60% of the residential customers have a PV system. Results validate the ability of using the DDQN control for voltage regulation in real time applications.

Many electrical distribution networks around the world are already experiencing the massive integration of distributed energy resources, in particular, residential solar photovoltaic (PV) systems. As networks become more observable and controllable, coordinated and active management of all available assets will be required to prevent high PV penetrations from affecting network integrity. This paper explores the benefits and implementation challenges of using Q-learning, a Reinforcement Learning technique, to actively control the on-load tap changer (OLTC) at primary substations and, thus, mitigate voltage rise issues in PV-rich distribution networks. The training process occurs in both offline and online modes. Furthermore, some adjustments are proposed to improve scalability. As a case study, a real Brazilian three-phase MV/LV distribution network with 5,000+ customers is used considering a high PV penetration. Controlling only the OLTC, results demonstrate the importance of adequate reward functions (targeted at reducing voltage problems) and size of the training dataset.

The growing integration of distributed energy resources (DER) into distribution networks is increasing the complexity of planning and operational tasks carried out by distribution network operators (DNOs). To achieve this in a timely manner, they need new advanced analysis tools to adequately quantify the impacts and the benefits from potential solutions to be seen in future distribution networks. In this context, this paper presents in detail the architecture and implementation of an advanced geographic information system (GIS)-based planning tool, named OpenGIS, to assess the impacts of DER on distribution networks, and to investigate potential solutions for thermal and/or voltage problems. OpenGIS provides a user-friendly graphical user interface, flexible analysis with detailed results in a GIS environment, and is built through the integration of free-license software packages. A real UK low voltage network with residential photovoltaic (PV) systems is used to demonstrate the different features of the tool.

Recently, several approaches have been proposed to mitigate the technical impacts caused by distributed generators in electrical energy distribution systems. Among these approaches one can detach the control scheme known as Volt/VAr, a centralized scheme that integrates voltage and reactive power control functions. In this context, this work aims to study the Volt/VAr control solved by an optimization tool, and focused on distribution systems with a high monitoring level and a massive integration of photovoltaic systems.

Recentemente, em paises desenvolvidos ou em desenvolvimento, os medidores de energia eletromecânicos vem sendo substituidos por uma infraestrutura avancada de medicao (AMI), em que os principais integrantes sao os medidores inteligentes, sistemas de comunicacao, e sistemas de gerenciamento de dados. Ao inves de disponibilizar apenas dados de consumo de energia, os medidores inteligentes disponibilizam medidas de grandezas variadas adquiridas no ponto de conexao dos consumidores. Os sistemas de comunicacao permitem acesso a estas medidas em tempo real ou quase real, e os sistemas de gerenciamento de dados sao essenciais para o processamento dos dados e obtencao de informacoes relevantes a partir destes. Embora o custo de instalacao da infraestrutura avancada de medicao seja elevado, quando se consideram os ganhos relacionados ao melhor gerenciamento dos sistemas de distribuicao, tal infraestrutura passa a ser economicamente atrativa. Neste contexto, este trabalho objetiva o estudo do uso de um unico metodo que utiliza dados de medidores inteligentes para o desempenho de multiplas funcoes do Sistema de Gerenciamento da Distribuicao, sao elas: (a) combate as Perdas Nao Tecnicas (PNTs); (b) localizacao de Faltas de Alta Impedância (FAIs); e (c) correcao da base de dados de topologia dos sistemas de distribuicao de energia eletrica.

A instalacao de sistemas fotovoltaicos de geracao distribuida vem se tornando cada vez mais economicamente atrativa devido a constante reducao dos custos de implantacao e as politicas governamentais de incentivo no Brasil, com enforque ao net metering. Como resultado, o que se ve e um numero crescente de sistemas fotovoltaicos nas redes de distribuicao, o que implica novos desafios operativos, especialmente relacionados a manutencao das tensoes de regime permanente dentro dos limites regulatorios quando do pico da geracao solar. Solucoes tradicionalmente utilizadas e baseadas unicamente no uso de bancos de capacitores, reguladores de tensao e transformadores OLTC (On Load Tap Changer) nas subestacoes por vezes se mostram ineficazes em redes com alta penetracao de geradores distribuidos. Neste contexto, o presente trabalho parte do pressuposto de que os inversores inteligentes dos sistemas fotovoltaicos devam ser utilizados para controlar ativamente a tensao da rede por meio da injecao/consumo de potencia reativa e propoe regras simples e intuitivas para atribuir uma curva de controle Volt-Var individualizada para cada gerador fotovoltaico, baseada em sua distância da subestacao, que procura mitigar as transgressoes de tensao e reduzir a injecao/consumo de potencia reativa pelos sistemas.