Survey of multi-agent systems for microgrid control

The generation of energy from renewable sources is subjected to very dynamic changes in environmental parameters and asset operating conditions. This is a very relevant issue to be considered when developing reliability studies, modeling asset degradation and projecting renewable energy production. To that end, Artificial Neural Network (ANN) models have proven to be a very interesting tool, and there are many relevant and interesting contributions using ANN models, with different purposes, but somehow related to real-time estimation of asset reliability and energy generation. This document provides a precise review of the literature related to the use of ANN when predicting behaviors in energy production for the referred renewable energy sources. Special attention is paid to describe the scope of the different case studies, the specific approaches that were used over time, and the main variables that were considered. Among all contributions, this paper highlights those incorporating intelligence to anticipate reliability problems and to develop ad-hoc advanced maintenance policies. The purpose is to offer the readers an overall picture per energy source, estimating the significance that this tool has achieved over the last years, and identifying the potential of these techniques for future dependability analysis.

A Review of the Use of Artificial Neural Network Models for Energy and Reliability Prediction. A Study of the Solar PV, Hydraulic and Wind Energy Sources

https://research.aalto.fi/files/36595757/CHEM_Kabugo_et_al_Industry_2020_ElePowEnrSyst.pdf

Industry 4.0 based process data analytics platform: A waste-to-energy plant case study

In 2015, the Zika virus spread from Brazil throughout the Americas, posing an unprecedented challenge to the public health community. During the epidemic, international public health officials lacked reliable predictions of the outbreak’s expected geographic scale and prevalence of cases, and were therefore unable to plan and allocate surveillance resources in a timely and effective manner. In this work, we present a dynamic neural network model to predict the geographic spread of outbreaks in real time. The modeling framework is flexible in three main dimensions (i) selection of the chosen risk indicator, i.e., case counts or incidence rate; (ii) risk classification scheme, which defines the high-risk group based on a relative or absolute threshold; and (iii) prediction forecast window (1 up to 12 weeks). The proposed model can be applied dynamically throughout the course of an outbreak to identify the regions expected to be at greatest risk in the future. The model is applied to the recent Zika epidemic in the Americas at a weekly temporal resolution and country spatial resolution, using epidemiological data, passenger air travel volumes, and vector habitat suitability, socioeconomic, and population data for all affected countries and territories in the Americas. The model performance is quantitatively evaluated based on the predictive accuracy of the model. We show that the model can accurately predict the geographic expansion of Zika in the Americas with the overall average accuracy remaining above 85% even for prediction windows of up to 12 weeks. Sensitivity analysis illustrated the model performance to be robust across a range of features. Critically, the model performed consistently well at various stages throughout the course of the outbreak, indicating its potential value at any time during an epidemic. The predictive capability was superior for shorter forecast windows and geographically isolated locations that are predominantly connected via air travel. The highly flexible nature of the proposed modeling framework enables policy makers to develop and plan vector control programs and case surveillance strategies which can be tailored to a range of objectives and resource constraints.

/pdf/a-dynamic-neural-network-model-for-predicting-risk-of-zika-22hmx7stjf.pdf

A dynamic neural network model for predicting risk of Zika in real-time

In modern era, the awareness of green energy technologies in the Microgrid (MG) is highly adopted in order to reduce the CO 2 emission and for a clean environment. The distributed energy resources, such as solar photo voltaic (PV), solar combine heat and power (CHP), diesel engines, small wind turbines and fuel cell technologies are evolving within the power system. The control and maintenance of this power have great effect on power systems. For optimal use of electric power in MGs, the Multi-Agent System (MAS) technology is adopted and has certain applications in the power systems. This research article mainly focuses on MAS technologies used for the control of MG, its optimization and market distribution. A fully controlled architecture of MG using MAS with different optimization techniques applied to renewable energy sources has been deliberate. Moreover, comparison of centralized and decentralized approach of a MG is also discussed in this article.

The research on multi-agent system for microgrid control and optimization

The solar photovoltaic (PV) energy has an important place among the renewable energy sources. Therefore, several researchers have been interested by its modelling and its prediction, in order to improve the management of the electrical systems which include PV arrays. Among the existing techniques, artificial neural networks have proved their performance in the prediction of the solar radiation. However, the existing neural network models don’t satisfy the requirements of certain specific situations such as the one analyzed in this paper. The aim of this research work is to supply, with electricity, a race sailboat using exclusively renewable sources. The developed solution predicts the direct solar radiation on a horizontal surface. For that, a Nonlinear Autoregressive Exogenous (NARX) neural network is used. All the specific conditions of the sailboat operation are taken into account. The results show that the best prediction performance is obtained when the training phase of the neural network is performed periodically.

https://hal.archives-ouvertes.fr/hal-01933133/document

A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation

The electrical networks are very complex systems, presently in full evolution. With the increasing penetration and apportionment over large areas of the renewable energies, the centralized nature of the power production evolves toward a more distributed form. In this context, the interest of the microgrids, as subcomponents of the main grid, rises especially by the specific services that they can provide. To ensure the stability and the dependability of a microgrid is a difficult task particularly in islanded mode. The microgrid is a mix of different types of elements and its structure may evolve. The multi-agents systems technique, with its distributed and adaptive character, can be an interesting tool for the control of each microgrid component and for the real time decision making related to the microgrid management. The paper starts with a presentation of microgrids and their specific issues, and follows with some basic concepts on multi-agents systems. Then, a review of the proposed techniques and algorithms that implies multi-agents systems in microgrids management is presented, focusing on the safety and the dependability in microgrids.

/pdf/multi-agent-systems-for-the-dependability-and-safety-of-1ddtw6s0ep.pdf

Multi-agent systems for the dependability and safety of microgrids

During the last decade, the smart grid (SG) concept has started to become a reality, mainly thanks to the technical progress achieved in telecommunications, informatics and power electronics, among other domains, leading to an evolution of the traditional electrical grid into an intelligent one. Nowadays, the SG can be seen as a system of smart systems that include cyber and physical parts from different technologies that interact with each other. In this context, intelligent buildings (IBs) constitute a paradigm in which such smart systems are able to guarantee the comfort of residents while ensuring an appropriate tradeoff of energy production and consumption by means of an energy management system (EMS). These interconnected EMSs remain the objective of potential cyber-attacks, which is a major concern. Therefore, this paper conducts a survey, from a multidisciplinary point of view, of some of the main security and privacy issues related to IBs as part of the SG, including an overview of EMS, smart meters, and the main communication networks employed to connect IBs to the overall SG. Future research directions towards a security enhancement from both technical and human perspectives are also provided.

https://www.mdpi.com/1996-1073/14/9/2733/pdf

Intelligent Buildings in Smart Grids: A Survey on Security and Privacy Issues Related to Energy Management

Solar radiation prediction has a great importance for many applications such as PV power forecasting and solar water heaters. The need of solar radiation prediction increase over time and certainly the accurate prediction can greatly improve the performance of these applications. In this paper a prediction of solar radiation for a winter day using ARMA model is performed. The performance of this model to predict the solar radiation has been validated for a real database. Simulations results show that the effectiveness of ARMA model is proven to predict especially the small variation of solar radiation.

/pdf/solar-radiation-prediction-for-a-winter-day-using-arma-model-4eblzh17m7.pdf

Solar radiation prediction for a winter day using ARMA model

The complexity and the decentralization of Micro-Grids have led to management and diagnosis issues because of using distributed power sources, especially the renewable energy sources. Wireless Sensor Networks can substitute part of the communication infrastructure of the Micro-Grid, it deploys between its elements in order to ensure data flow in real time. It allows energy management applications to have more interesting cost and efficiency. The present work discusses the Wireless Sensor Networks usage dedicated to energy management and default diagnosis in Micro-Grids.

/pdf/wireless-sensors-networks-applications-for-micro-grids-2lblhktatn.pdf

Zina Boussaada

Papers

A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation

Multi-agent systems for the dependability and safety of microgrids

Intelligent Buildings in Smart Grids: A Survey on Security and Privacy Issues Related to Energy Management

Solar radiation prediction for a winter day using ARMA model

Wireless Sensors Networks Applications For Micro-Grids Management: State of Art