Research on Hybrid Renewable Energy Systems with Fault Detection Technology

Early and accurate fault detection and diagnosis for renewable energy systems can increase their safety and ensure the continuity of their service. This paper presents a comprehensive review of different fault detection and diagnosis methods for hybrid renewable energy systems consisting of a wind turbine power generator, a PV （photovoltaic） array, a PEM （polymer electrolyte membrane） fuel cell and a battery storage system. The need of batteries to store the generated power from the solar panel, wind turbine or PEM fuel cell is also emphasized. Finally, an overview of the current methods used in the diagnosing of the lead-acid battery degradation is given.

Guest Editorial for Special Issue on Control and Optimization in Renewable Energy Systems

I.I NTRODUCTION W ITH the advent of low-carbon economy,there has been a growing interest in harnessing renewable energy resources particularly for electricity generation.Renewable energy resources are advocated for the economic and environ-

A Review on Renewable Energy Systems for Irrigation in Arid and Semi-Arid Regions

The lack of water in arid and semi-arid regions has often limited agricultural production. Indeed, even where water is available for irrigation, the lack of electricity, as well as the high costs of diesel, has created constraints on small farmers. The purpose of this research is to review the renewable energy potential available in arid and semi-arid zones that can be used for irrigation as a substitute for fossil fuels. In this review, the solar thermal irrigation, solar photovoltaic (PV) irrigation, wind pumping and biomass pumping are discussed. The comparison of different hybrid pumping systems and analyses of renewable sources irrigation assessment in arid and semi-arid regions of Mozambique also are discussed. The results of this study showed that there are still certain technological limitations regarding the use of solar thermal energy for irrigation. As far as wind power is concerned, the analysis of the pumping water life cycle cost showed that the wind power water pumping system is more economical and viable compared to the diesel based system. However, the study concluded that photovoltaic solar energy has been shown to be more viable for pumping water for irrigation in arid and semi-arid regions.

Planning of distributed renewable energy systems under uncertainty based on statistical machine learning

The development of distributed renewable energy,such as photovoltaic power and wind power generation,makes the energy system cleaner,and is of great significance in reducing carbon emissions.However,weather can affect distributed renewable energy power generation,and the uncertainty of output brings challenges to uncertainty planning for distributed renewable energy.Energy systems with high penetration of distributed renewable energy involve the high-dimensional,nonlinear dynamics of large-scale complex systems,and the optimal solution of the uncertainty model is a difficult problem.From the perspective of statistical machine learning,the theory of planning of distributed renewable energy systems under uncertainty is reviewed and some key technologies are put forward for applying advanced artificial intelligence to distributed renewable power uncertainty planning.

CT-NET: A Novel Convolutional Transformer-Based Network for Short-Term Solar Energy Forecasting Using Climatic Information

Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.

Analysing Different Microgeneration Systems for Portuguese Residential Sector

The main purpose of this article is to perform a technical-economic analysis of different microgeneration systems （photovoltaic and wind turbine systems） that can be installed in a single-family house. One of the strategies for improving energy performance of buildings is the installation of microgeneration systems. This will enable Portugal to meet the goal regarding the share of renewable sources on gross final energy consumption imposed by the European Commission climate change and energy package for 2020. The analysis of four different micro-generation systems will take into account the local availability of renewable resources and market technologies and the new Portuguese law concerning microgeneration to promote renewable energy sources in households. The Portuguese microgeneration legal framework is also highlighted.

Identification of Type of a Fault in Distribution System Using Shallow Neural Network with Distributed Generation

A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stability loss,failure re-closure,fluctuations in voltage,etc.And thereby,it demands immediate attention in identifying the location&type of a fault without delay especially when occurred in a small,distributed generation system,as it would adversely affect the overall system and its operation.In the past,several methods were proposed for classification and localisation of a fault in a distributed generation system.Many of those methods were accurate in identifying location,but the accuracy in identifying the type of fault was not up to the acceptable mark.The proposed work here uses a shallow artificial neural network(sANN)model for identifying a particular type of fault that could happen in a specific distribution network when used in conjunction with distributed generators.Firstly,a distribution network consisting of two similar distributed generators(DG1 and DG2),one grid,and a 100 Km distribution line is modeled.Thereafter,different voltages and currents corresponding to various faults(line to line,line to ground)at different locations are tabulated,resulting in a matrix of 500×18 inputs.Secondly,the sANN is formulated for identifying the types of faults in the system in which the above-obtained data is used to train,validate,and test the neural network.The overall result shows an unprecedented almost zero percent error in identifying the type of the faults.

INTEGRATED ARCHITECTURAL AND ENGINEERING DESIGN STRATEGIES FOR A ZERO-ENERGY BUILDING:Illinois Institute of Technology’s Design Entry for the 2018 U.S.Department of Energy Race to Zero(Solar Decathlon Design Challenge)

This paper describes the design of InterTech,a zero-energy mixed-use student residence hall,developed in 2018 by an interdisciplinary team of Illinois Institute of Technology(Illinois Tech)students for the U.S.Department of Energy Solar Decathlon Design Challenge,formerly known as Race to Zero.The main focus is the team’s integrated and iterative approach,which blended architectural design and engineering concepts and led to achieving the high-performance goal.InterTech aims to provide an innovative housing solution to Illinois Institute of Technology’s graduate students and their families.Located along State Street in between Illinois Tech’s main campus and downtown Chicago,it offers a mix of living options providing both independence and access to the campus and to the city.In addition to the residential program,the project includes a small grocery/cafe con-nected to an outdoor public plaza,and an underground garage.Energy modeling was introduced in the early design stages.The potential of on-site renewable energy generation defined the project’s target Energy Use Intensity(EUI)of 37 kBtu/sqft.Several passive and active strategies were implemented to reduce the building’s total energy needs and meet the target EUI.The implementation of energy conservation measures led to a 25%reduction of the building’s cooling load and a 33%reduction of the heating load.A design EUI of 28 kBtu/sqft was calculated,validating that this design met and exceeded the zero-energy goal.

Intelligent Energy Management Strategy and Sizing Methodology for Hybrid Systems in Isolated Regions

In this study,a comprehensive approach is presented for the sizing and management of hybrid renewable energy systems(HRESs)that incorporate a variety of energy sources,while emphasizing the role of artificial neural networks(ANNs)in system management.For optimal sizing of an HRES,the monthly average method wherein historical weather data are used to calculate the monthly averages of solar irradiance and wind speed,offering a well-balanced strategy for system sizing.This ensures that the HRES is appropriately scaled to meet the actual energy requirements of the specified location,avoiding the pitfalls of over-and under-sizing,and thereby enhancing the operational efficiency.Furthermore,the study details a cutting-edge strategy that employs ANNs for managing the inherent complexities of HRESs.It elaborates on the design,modeling,and control strategies for the HRES components by utilizing Matlab/Simulink for implementation.The findings demonstrate the proficiency of the ANN-based power manager in determining the operational modes guided by a specifically designed flowchart.By integrating ANN-driven energy management strategies into an HRES,the proposed approach marks a significant advancement in system adaptability,precision control,and efficiency,thereby maximizing the effective utilization of renewable resources.

THE MIND,BODY&SPIRITS INSPIRED DINING ORGANIC RESTAURANT

INTRODUCTION The new Mind,Body&Spirits Inspired Dining Organic Restaurant,located at 301 S.Main Street in downtown Rochester,MI,opened in November of 2008.It is located on the southwest corner of S.Main Street and W.Third Street.It is housed in an existing two-story brick building with a full basement and has a New Greenhouse/Kitchen/Restrooms/Dining Deck Addition located in the former rear parking lot area to the west.

Physics Insight of the Inertia of Power Systems and Methods to Provide Inertial Response

The growth of renewable energy reduces the moment of inertia for the synchronous AC grid,so the authors put forward two basic questions:1)What is the physics insight that a synchronous AC grid needs for mechanical inertia?2)How to provide inertial response for the power grid dominated with renewable energy?Based on Einstein’s special relativity and the Lorentz transformation,these papers illustrates that the nature of the inertia of the AC grid comes from the relativity of the electromagnetic field and motion,and from the strong coupling between them.According to their nature,the inertial response of the synchronous generator is self-proven.By contrast,the converter for the grid-connection of renewable energies used various algorithms in order to provide virtual inertia.But because algorithms do not rebuild the coupling between electromagnetic fields and motion,it is doubtful whether they can provide inertia and inertial responses.Therefore,the authors propose that there is a need to build extra electromagnetic fields and motion coupling for grids with high penetration rates of renewable energy.Therefore,a new grid-connection technology via Motor-Generator Pair(MGP)is discussed.The electromagnetic-motion coupling of the MGP is analyzed,and the results of simulation and experimental studies are also reported.

Modular System of Cascaded Converters Based onModel Predictive Control

A modular system of cascaded converters based on model predictive control(MPC)is proposed to meet the application requirements ofmultiple voltage levels and electrical isolation in renewable energy generation systems.The system consists of a Buck/Boost+CLLLC cascaded converter as a submodule,which is combined in series and parallel on the input and output sides to achieve direct-current(DC)voltage transformation,bidirectional energy flow,and electrical isolation.The CLLLC converter operates in DC transformer mode in the submodule,while the Buck/Boost converter participates in voltage regulation.This article establishes a suitable mathematical model for the proposed system topology,and uses MPC to control the system based on this mathematical model.Module parameters are designed and calculated,and simulation is built in MATLAB/Simulink to complete the simulation comparison experiment between MPC and traditional proportional integral(PI)control.Finally,a physical experimental platform is built to complete the physical comparison experiment.The simulation and physical experimental results prove that the control accuracy and response speed ofMPC are better than traditional PI control strategy.