建筑光伏储能系统优化管理策略及影响因素研究  

Research on Optimized Management Strategy for Building Photovoltaic Energy System and the Influencing Factors

作　　者：郭浩然 李乾 谈卓越 王慧龙 Guo Haoran;Li Qian;Tan Zhuoyue;Wang Huilong(College of Civil and Transportation Engineering,Shenzhen University,Shenzhen Guangdong 518052)

机构地区：[1]深圳大学土木与交通工程学院,广东深圳518052

出　　处：《中外能源》2024年第5期35-43,共9页Sino-Global Energy

基　　金：国家自然科学基金青年项目“室温设定值调节下空调能耗回调特性及柔性用能控制方法”(编号:52308104);深圳可持续发展科技专项(双碳专项)“建筑高效节能及电力柔性技术研究与应用示范”(编号:KCXST20221021111203007)。

摘　　要：在建筑能源系统中引入光伏已成为可持续能源的有效解决方案之一。然而光伏发电受时间和环境影响明显,其变化规律很难与建筑自身用能需求完全匹配。为了解决该问题,在峰谷电价背景下,提出一种新型的基于发电和用电预测的建筑光伏储能系统优化管理策略,并重点研究实际运行工况下,发电量和用电量预测精度、建筑层数、季节类型对优化管理策略性能的影响。首先基于极端梯度提升(XGBoost)算法,开发了建筑用电量和光伏发电量逐时预测模型。在此基础上,针对光伏、蓄电池、电网及建筑4个模块,利用遗传算法优化未来24h蓄电池逐时充放电量,从而实现系统日用电成本最小化。研究发现,在发电量与用电量比较接近时,优化管理策略相比传统策略有显著的性能提升,特别适用于不高于2层的建筑,有望在城镇中广泛推广。而对于城市高层建筑,在光伏发电量远低于建筑用电量的场景下,优化管理策略虽然优势并不显著,但效果仍优于传统策略。研究还发现,对于不高于2层的建筑,即使发、用电量预测精度不高,优化管理策略依然性能良好,且随着预测精度的上升性能会进一步提升。The introduction of photovoltaics into building energy systems has become one of the effective solutions for sustainable energy.However,photovoltaic power generation is greatly affected by time and environment,and its change rule is difficult to perfectly match the energy demand of the building itself.In order to solve this problem,an optimized management strategy for building photovoltaic energy storage system based on power generation and power consumption prediction is proposed against the background of peak-valley electricity price,and the influences of the accuracy of power generation and power consumption prediction,the number of building floors and the season type on the performance of optimized management strategy under actual operating conditions are studied.Based on eXtreme Gradient Boosting(XGBoost)algorithm,the hourly prediction model of building power consumption and photovoltaic power generation is developed.On this basis,genetic algorithm is used to optimize the hourly charging and discharging capacity of the battery in the next 24 hours for 4 modules including photovoltaic,battery,power grid and building,so as to minimize the daily electricity cost of the system.It is found that the optimized management strategy has significantly better performance than traditional strategy when power generation is close to power consumption.It is especially suitable for buildings with no more than 2 floors,and is expected to be widely promoted in cities and towns.For urban high-rise buildings,in the scenario where photovoltaic power generation is much lower than building power consumption,the optimized management strategy is better than the traditional strategy although the advantage is not significant.It is also found that for buildings with no more than 2 floors,even if the accuracy of power generation and power consumption prediction is not high,the optimized management strategy still performs well,and its performance will be further improved with the increase of prediction accuracy.

关 键 词：建筑光伏 储能 能源管理策略 电量预测 建筑层数 季节类型 

分 类 号：TU18[建筑科学—建筑理论]