基于卷积和共享权系数长短时记忆网络时融合机制在风速预测上的应用研究

针对对于风能规划和应用都具有重大影响的风速存在强随机性问题,该文提出结合卷积神经网络（CNN）和共享权重长短期记忆网络（SWLSTM）的空时融合模型（CSWLSTM）,充分提取风速序列中蕴含的空域和时域信息,以提升预测精度。此外,为了获得可靠的风速概率预测结果,提出一种新的结合CNN、SWLSTM和高斯过程回归（GPR）的混合模型,称为 CSWLSTM-GPR。将CSWLSTM-GPR应用于中国内蒙古风速预测案例,从点预测精度、区间预测适用性和概率预测综合性能3个方面与相同结构的CNN和SWLSTM模型的风速预测方法进行比较。CSWLSTM-GPR的可靠性测试保证了预测结果的可靠性和说服力。实验结果表明,CSWLSTM-GPR在风速预测问题上能获得高精度的点预测、合适的预测区间和可靠的概率预测结果,也充分展现了该研究所提出CSWLSTM在风速预测方面具有较好的应用潜力。     

Experimental performance assessment of an online energy management strategy for varying renewable power production suppression

Lately, interest in renewable sources, especially wind and solar energy, has shown a significant increase in all over the world that mostly depends on climate-threatening conventional fossil fuels. Besides, hybrid use of these power sources with suitable back-up units provides many advantages compared to sole use of these sources. In this regard, a hybrid system consisting of a wind turbine for utilizing the wind energy, photovoltaic panels for solar energy, fuel cell for providing back-up power and a battery unit for storing the possible excess energy production and supplying the transient load is considered in this study. Experimental assessment of this system in different case studies including the real time measured dynamic power demand of an office block is realized. The collaborative actions of the proposed hybrid system with a fuzzy logic based energy management strategy during fluctuations of renewable-based power production are investigated. Thus, results of this study may be valuable for evaluating the feasibility of stand-alone hybrid renewable energy units for future power systems.     

An overview of the environmental,economic, and material developments of the solar and wind sources coupled with the energy storage systems

There is a constant growth in energy consumption and consequently energy generation around the world. During the recent decades, renewable energy sources took heed of scientists and policy makers as a remedy for substituting traditional sources. Wind and photovoltaic (PV) are the least reliable sources because of their dependence on wind speed and irradiance and therefore their intermittent nature. Energy storage systems are usually coupled with these sources to increase the reliability of the hybrid system. Environmental effects are one of the biggest concerns associated with the renewable energy sources. This study summarizes the last and most important environmental and economic analysis of a grid‐connected hybrid network consisting of wind turbine, PV panels, and energy storage systems. Focusing on environmental aspects, this paper reviews land efficiency, shaded analysis of wind turbines and PV panels, greenhouse gas emission, wastes of wind turbine and PV panels' components, fossil fuel consumption, wildlife, sensitive ecosystems, health benefits, and so on. A cost analysis of the energy generated by a hybrid system has been discussed. Furthermore, this study reviews the latest technologies for materials that have been used for solar PV manufacturing. This paper can help to make a right decision considering all aspects of installing a hybrid system. Copyright © 2017 John Wiley & Sons, Ltd.     

Optimal management of microgrids including renewable energy scources using GPSO-GM algorithm

Environmentally friendly energy sources with high power quality or reliability and low costs are regarded as an effective solution for energy supply problems arising from use of conventional methods. Presented in this paper, gives an optimal management strategy of PV/wind/diesel independent hybrid systems for supplying required energy in autonomous microgrids. A new optimization problem is formulated for minimizing the capital investment and fuel costs of the system. To solve the proposed optimization problem a novel algorithm, named Guaranteed convergence Particle Swarm Optimization with Gaussian Mutation (GPSO-GM), is developed. Two operators, namely mutation and guaranteed convergence, are added to PSO in order to help finding more accurate results and increasing the speed of calculations. The performance of the proposed strategy is evaluated in two case studies.     

A corrected hybrid approach for wind speed prediction in Hexi Corridor of China

Wind energy has been well recognized as a renewable resource in electricity generation, which is environmentally friendly, socially beneficial and economically competitive. For proper and efficient evaluation of wind energy, a hybrid Seasonal Auto-Regression Integrated Moving Average and Least Square Support Vector Machine (SARIMA-LSSVM) model is significantly developed to predict the mean monthly wind speed in Hexi Corridor. The design concept of combining the Seasonal Auto-Regression Integrated Moving Average (SARIMA) method with the Least Square Support Vector Machine (LSSVM) algorithm shows more powerful forecasting capacity for monthly wind speed prediction at wind parks, when compared with the single Auto-Regression Integrated Moving Average (ARIMA), SARIMA, LSSVM models and the hybrid Auto-Regression Integrated Moving Average and Support Vector Machine (ARIMA-SVM) model. To verify the developed approach, the monthly data from January 2001 to December 2006 in Mazong Mountain and Jiuquan are used for model construction and model testing. The simulation and hypothesis test results show that the developed method is simple and quite efficient.     

Wind speed forecast model for wind farm based on a hybrid machine learning algorithm

This paper presents a new strategy for wind speed forecasting based on a hybrid machine learning algorithm, composed of a data filtering technique based on wavelet transform (WT) and a soft computing model based on the fuzzy ARTMAP (FA) network. The prediction capability of the proposed hybrid WT+FA model is demonstrated by an extensive comparison with some other existing wind speed forecasting methods. The results show a significant improvement in forecasting error through the application of a proposed hybrid WT+FA model. The proposed wind speed forecasting strategy is applied to real data acquired from the North Cape wind farm located in PEI, Canada.     

Experimental investigation of power management and control of a PV/wind/fuel cell/battery hybrid energy system microgrid

This paper presents an experimental study of a standalone hybrid microgrid system. The latter is dedicated to remote area applications. The system is a compound that utilizes renewable sources that are Wind Generator (WG), Solar Array (SA), Fuel Cell (FC) and Energy Storage System (ESS) using a battery. The power electronic converters play a very important role in the system; they optimize the control and energy management techniques of the various sources. For wind and solar subsystem, the speed and Single Input Fuzzy Logic (SIFL) controllers are used respectively to harvest the maximum power point tracking (MPPT). To maintain a balance of energy in the hybrid system, an energy management strategy based on the battery state of charge (SOC) has been developed and implemented experimentally. The AC output voltage regulation was achieved using a Proportional Integral (PI) controller to supply a resistive load with constant amplitude and frequency. According to the obtained performances, it was concluded that the proposed system is very promising for potential applications in hybrid renewable energy management systems.     

Design and evaluation of PV-wind hybrid system with hydroelectric pumped storage on the National Power System of Egypt

National and international policies encourage increased penetration of solar and wind energy into electrical networks in order to reduce greenhouse gas emission. Solar radiation and wind speed variations complicate the integration of wind and solar generation into power systems and delay the transition of these sources from centralized to distributed energy sources. The increased penetration of nontraditional energy sources into the electric grid stimulates the demand for large capacities in the field of energy storage. A mathematical model, which describes the operation of a proposed hybrid system, including solar PV, wind energy, and a pumped storage hydroelectric power plant is developed in this paper. This hydropower plant utilizes seawater as a lower reservoir, and only a tank has to be built in order to reduce the installation cost of the storing system. The pumped storage power plant used for compensation of the variation of the output energy from the PV and wind power plants by discharging water from the upper reservoir, which is previously pumped in the case of surplus energy from PV and wind turbine power plants. The impact of the proposed system on the grid utility is investigated in accordance with the values of energy exchange (deficits and surpluses of energy) between the considered hybrid system and the grid. The optimum design is determined by the pump and turbine capacities, upper reservoir volume, and the volume of water left in the tank for emergencies. Different scenarios of the optimum operations are presented for analysis. The results obtained from the examined scenarios indicate the ability of such a hybrid energy system to reduce the exchange of energy with the grid. This paper indicates the technical feasibility of seawater pumped-storage hydropower plant for increasing the Egyptian national grid’s ability to accept high integration of renewable energy sources.     

Multi-objective optimal design of hybrid renewable energy systems using PSO-simulation based approach

Recently, the increasing energy demand has caused dramatic consumption of fossil fuels and unavoidable raising energy prices. Moreover, environmental effect of fossil fuel led to the need of using renewable energy (RE) to meet the rising energy demand. Unpredictability and the high cost of the renewable energy technologies are the main challenges of renewable energy usage. In this context, the integration of renewable energy sources to meet the energy demand of a given area is a promising scenario to overcome the RE challenges. In this study, a novel approach is proposed for optimal design of hybrid renewable energy systems (HRES) including various generators and storage devices. The ε-constraint method has been applied to minimize simultaneously the total cost of the system, unmet load, and fuel emission. A particle swarm optimization (PSO)-simulation based approach has been used to tackle the multi-objective optimization problem. The proposed approach has been tested on a case study of an HRES system that includes wind turbine, photovoltaic (PV) panels, diesel generator, batteries, fuel cell (FC), electrolyzer and hydrogen tank. Finally, a sensitivity analysis study is performed to study the sensibility of different parameters to the developed model.     

Techno-economical evaluation of a hydrogen refuelling station powered by Wind-PV hybrid power system: A case study for İzmir-Çeşme

Hydrogen fuelling station is an infrastructure for the commercialisation of hydrogen energy utilising fuel cells, particularly, in the automotive sector. Hydrogen fuel produced by renewable sources such as the solar and wind energy can be an alternative fuel to depress the use of fuels based on fossil sources in the transport sector for sustainable clean energy strategy in future. By replacing the primary fuel with hydrogen fuel produced using renewable sources in road transport sector, environmental benefits can be achieved. In the present study, techno-economic analysis of hydrogen refuelling station powered by wind-photovoltaics (PV) hybrid power system to be installed in ?zmir-Çe?me, Turkey is performed. This analysis is carried out to a design of hydrogen refuelling station which is refuelling 25 fuel cell electric vehicles on a daily basis using hybrid optimisation model for electric renewable (HOMER) software. In this study, National Aeronautics and Space Administration (NASA) surface meteorology and solar energy database were used. Therefore, the average wind speed during the year was assessed to be 5.72 m/s and the annual average solar irradiation was used to be 5.08 kW h/m²/day for the considered site. According to optimisation results obtained for the proposed configuration, the levelised cost of hydrogen production was found to be US $7.526–7.866/kg in different system configurations. These results show that hydrogen refuelling station powered by renewable energy is economically appropriate for the considered site. It is expected that this study is the pre-feasibility study and obtained results encougare the hydrogen refuelling station to be established in Turkey by inventors or public institutions.     

基于混合深度学习的风电功率预测及一次调频应用

为了解决高比例不确定性风电接入电力系统带来强烈调频需求的问题,提出了基于混合深度学习模型的风电功率预测及其一次调频应用方法。首先,采用孤立森林(Isolated Forest, IF)对历史数据进行异常值处理,提高数据质量,其次,构建卷积神经网络(Convolutional Neural Network, CNN)、双向长短期记忆(Bidirectional Long Short Term Memory, BiLSTM)和注意力机制(Attention Mechanism, AM)的混合深度学习模型对风电功率进行预测。最后,依据功率预测精度配置超级电容器储能,设计储能调频控制原则,弥补风电机组自身预测误差,并协同风电机组参与电力系统一次调频。基于预测结果为4台风电发电机组2个负荷区域仿真系统配置超级电容器储能系统,利用digsilent平台进行了风预测误差和负荷波动下的一次调频仿真。结果表明：所提IF-CNN-BiLSTM-AM模型比BP和LSTM基准模型预测误差(MSE)降低了81.53%和51.44%,具有最优的预测性能;设计的风储一次调频模型与原则可有效应对风电预测误差和负荷波动...     

An investigation of variable speed operation of diesel generators in hybrid energy systems

This paper provides a preliminary assessment of the performance and economic potential of a hybrid energy system (wind/diesel) power system which includes a variable speed diesel generator. Recent development in power electronics would be utilized to allow asynchronous operation of the diesel generator, while simultaneously delivering constant frequency electric power to the local electrical grid. In addition to the variable speed diesel, the system can include wind and/or solar electric sources. A hybrid energy system model recently developed at the University of Massachusetts is used to simulate this system configuration and other more conventional wind/diesel hybrid energy systems. Experimental data from a series of variable speed diesel generator tests were used to generate a series of fuel consumption curves used in the analytical model. In addition to performance (fuel savings) comparisons for fixed and variable speed systems, economic cost of energy calculations for the various system designs are presented. It is shown that the proposed system could offer both performance and economic advantages.     

考虑预测误差分析的混合储能补偿优化策略

为提高风电场预测功率精度,对于风电场和混合储能构成的风储混合系统,提出基于预测信息搭建的混合储能补偿方案。首先,依据风电预测误差进行概率统计分析,提出风电功率预测误差的分层补偿策略,制定针对补偿预测误差的允许误差域及置信区间补偿域。其次,利用储能对不同误差层的预测误差给出相应的储能补偿方案,基于小波包分解将超出区域外待补偿预测误差分解,通过不平衡功率DFT分频法确定临界点作为功率型储能和能量型储能的目标分配值,对于荷电状态越限问题通过自适应模糊控制进行二次修正。最后,以新疆某风电场为例进行仿真分析,结果表明所提策略可有效减少风电功率预测误差。     

Techno-economical study of hybrid power system for a remote village in Algeria

The share of renewable energy sources in Algeria primary energy supply is relatively low compared with European countries, though the trend of development is positive. One of the main strategic priorities of NEAL (New Energy Algeria), which is Algeria's renewable energy agency (government, Sonelgaz and Sonatrach), is striving to achieve a share of 10–12% renewable energy sources in primary energy supply by 2010.This article presents techno-economic assessment for off-grid hybrid generation systems of a site in south western Algeria. The HOMER model is used to evaluate the energy production, life-cycle costs and greenhouse gas emissions reduction for this study. In the present scenario, for wind speed less than 5.0 m/s the existing diesel power plant is the only feasible solution over the range of fuel prices used in the simulation. The wind diesel hybrid system becomes feasible at a wind speed of 5.48 m/s or more and a fuel price of 0.162$/L or more. If the carbon tax is taken into consideration and subsidy is abolished, then it is expected that the hybrid system will become feasible. The maximum annual capacity shortage did not have any effect on the cost of energy, which may be accounted for by larger sizes of wind machines and diesel generators.     

数据驱动的时间注意力卷积风电功率预测模型

由于风电受气象特征影响大,风能波动性和间歇性强,导致快速、精准的风电预测成为一个难题。对此,该文提出一种基于数据驱动的时间注意力卷积网络的风电功率预测方法。首先,将来自风力机和数据采集（SCADA）系统的数据进行清洗;然后采用可并行计算的时间卷积网络,并加入Attention机制突出关键特征的影响,使模型训练速度和预测精度得到有效提升。实验结果表明,该文所提方法与其他方法相比可更准确地减少数据噪声,同时有更高的预测精度和更快的训练速度。     

A novel application of artificial neural network for wind speed estimation

Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.     

Wind energy potential assessment at four typical locations in Ethiopia

The wind energy potential at four different sites in Ethiopia – Addis Ababa (09:02N, 38:42E), Mekele (13:33N, 39:30E), Nazret (08:32N, 39:22E), and Debrezeit (8:44N, 39:02E) – has been investigated by compiling data from different sources and analyzing it using a software tool. The results relating to wind energy potential are given in terms of the monthly average wind speed, wind speed probability density function (PDF), wind speed cumulative density function (CDF), and wind speed duration curve (DC) for all four selected sites. In brief, for measurements taken at a height of 10 m, the results show that for three of the four locations the wind energy potential is reasonable, with average wind speeds of approximately 4 m/s. For the fourth site, the mean wind speed is less than 3 m/s. This study is the first stage in a longer project and will be followed by an analysis of solar energy potential and finally the design of a hybrid standalone electric energy supply system that includes a wind turbine, PV, diesel generator and battery.     

A comprehensive method for optimal power management and design of hybrid RES-based autonomous energy systems

The power management strategy (PMS) plays an important role in the optimum design and efficient utilization of hybrid energy systems. The power available from hybrid systems and the overall lifetime of system components are highly affected by PMS. This paper presents a novel method for the determination of the optimum PMS of hybrid energy systems including various generators and storage units. The PMS optimization is integrated with the sizing procedure of the hybrid system. The method is tested on a system with several widely used generators in off-grid systems, including wind turbines, PV panels, fuel cells, electrolyzers, hydrogen tanks, batteries, and diesel generators. The aim of the optimization problem is to simultaneously minimize the overall cost of the system, unmet load, and fuel emission considering the uncertainties associated with renewable energy sources (RES). These uncertainties are modeled by using various possible scenarios for wind speed and solar irradiation based on Weibull and Beta probability distribution functions (PDF), respectively. The differential evolution algorithm (DEA) accompanied with fuzzy technique is used to handle the mixed-integer nonlinear multi-objective optimization problem. The optimum solution, including design parameters of system components and the monthly PMS parameters adapting climatic changes during a year, are obtained. Considering operating limitations of system devices, the parameters characterize the priority and share of each storage component for serving the deficit energy or storing surplus energy both resulted from the mismatch of power between load and generation. In order to have efficient power exploitation from RES, the optimum monthly tilt angles of PV panels and the optimum tower height for wind turbines are calculated. Numerical results are compared with the results of optimal sizing assuming pre-defined PMS without using the proposed power management optimization method. The comparative results present the efficacy and capability of the proposed method for hybrid energy systems.     

Prospects of renewable energy - a feasibility study in the Australian context

Given the recent increasing public focus on climate change issues, there is a need for robust, sustainable and climate friendly power transmission and distribution systems that are intelligent, reliable, and green. Current power systems create environmental impacts as well as contributing to global warming due to their utilization of fossil fuels, especially coal, as carbon dioxide is emitted into the atmosphere. In contrast to fossil fuels, renewable energy is starting to be used as the panacea for solving climate change or global warming problems. This paper describes a feasibility study undertaken to investigate the potentialities of renewable energy including the prospective locations in Australia for renewable energy generation, in particular solar and wind energy. Initially, a hybrid model has been developed to investigate the prospects of wind energy for typical Australian region considering production cost, cost of energy, emission production and contribution from renewable energy using the Hybrid Optimization Model for Electric Renewable (HOMER), a computer model developed by the USA’s National Renewable Energy Laboratory (NREL). This model also explores suitable places around Australia for wind energy generation using statistical analysis. Subsequently, the usefulness of solar energy in the Australian context and suitable locations for solar energy generation are also investigated using a similar hybrid model. Finally, the model has been developed to investigate the prospects of renewable energy in particular wind and solar energy including specific locations in Australia that would be suitable for both wind and solar energy generation. From simulation analysis it is clearly observed that Australia has enormous potentialities for substantially increased use of renewable energy; a large penetration of renewable energy sources into the national power system would reduce CO₂ emissions significantly, contributing to the reduction of global warming.     

The achievement,significance and future prospect of China's renewable energy initiative

China's high-speed economic growth and ambitious urbanization depend heavily on the massive consumption of fossil fuel. However, the over-dependence on the depleting fossil fuels causes severe environmental problems, making China the largest energy consumer and the biggest CO₂ emitter in the world. Faced with significant challenges in terms of managing its environment and moving forward with the concept of sustainable economic development, the Chinese government plans to move away from fossil fuels and rely on renewables such as hydropower, wind power, solar power, biomass power and nuclear power. In this paper, the current status of China's renewable energy deployment and the ongoing development projects are summarized and discussed. Most recent developments of major renewable energy sources are clearly reviewed. Additionally, the renewable energy development policies including laws and regulations, economic encouragement, technical research and development are also summarized. This study showcases China's achievements in exploiting its abundant domestic renewable energy sources to meet the future energy demand and reducing carbon emissions. To move toward a low carbon society, technological progress and policy improvements are needed for improving grid access (wind), securing nuclear fuel supplies and managing safety protocols (nuclear), integrating supply chains to achieve indigenous manufacture of technologies across supply chains (solar). Beyond that, a preliminary prediction of the development of China's future renewable energy developments, and proposes targeted countermeasures and suggestions are proposed. The proposal involves developing smart-grid system, investing on renewable energy research, improving the feed-in tariff system and clarifying the subsidy system.