返回
ANN-based model predictive control for optimizing space cooling management
DOI:10.1016/j.energy.2025.136469.png)
摘要
En 中文
本研究将人工神经网络整合到模拟与优化框架中,以实现对住宅空间制冷的模型预测控制(MPC)。基于天气预报,该框架提供每日规划周期内的最优设定点调度方案,以降低能耗、成本及居住者的热不适感。采用多目标优化方法,旨在最小化系统运行成本及一种新型函数——舒适度惩罚函数,该函数量化全天潜在的居住者不适小时数。采用遗传算法进行优化,而前馈神经网络被训练以复制和预测建筑-设备系统的行为。前馈神经网络被训练用于预测室内温度和制冷负荷,其准确性与建筑模型输出相比表现出良好的效果。在获得帕累托前沿后,最优解与典型的夏季控制策略进行比较。结果表明,在不影响其他目标的情况下,潜在节能最高可达49%,或同时改善两个目标,制冷成本降低30%,舒适度惩罚(乌托邦准则)降低27%。这些发现表明,当设计合理时,代理模型能够准确预测建筑-设备动态,并以最小的计算成本提供可靠的优化结果。
Keyword:
Artificial neural networks
Model predictive control
Thermal comfort
Genetic algorithm
HVAC systems
Multi-objective optimization
期刊
IF:
9.4
论文数:
4.2W
被引数:
20.2W
机构
引用论文
Economic model predictive control for demand flexibility of a residential building住宅建筑需求灵活性的经济模型预测控制
ENERGY
IF9.4
Model predictive control for multi-zone Variable Air Volume systems based on artificial neural networks基于人工神经网络的多区域变风量系统模型预测控制
Multi-stage and multi-objective optimization for energy retrofitting a developed hospital reference building: A new approach to assess cost-optimality
APPLIED ENERGY
IF11
Supervisory model predictive controller (MPC) for residential HVAC systems: Implementation and experimentation on archetype sustainable house in Toronto住宅HVAC系统的监督模型预测控制器 (MPC): 多伦多原型可持续住宅的实施和实验
ENERGY AND BUILDINGS
IF7.1
Quantification of energy savings from an awareness program using NARX-ANN in an educational building
ENERGY AND BUILDINGS
IF7.1
A review on simulation-based optimization methods applied to building performance analysis
APPLIED ENERGY
IF11
An integrated model predictive control approach for optimal HVAC and energy storage operation in large-scale buildings大型建筑中HVAC和储能优化运行的集成模型预测控制方法
APPLIED ENERGY
IF11
Modelling and flexible predictive control of buildings space-heating demand in district heating systems区域供热系统中建筑物空间供热需求的建模和灵活预测控制
ENERGY
IF9.4

