Application of Deep Learning Model in Building Energy Consumption Prediction

Abstract

In order to achieve China’s energy conservation and emission reduction goal of peaking carbon dioxide emissions around 2030, it is of great significance. An important means of building energy conservation and emission reduction is the fine management of building energy consumption, which is based on the accurate prediction of building energy consumption, so as to support the optimal management of building operation and achieve the goal of energy conservation and emission reduction. This paper puts forward the evaluation indexes of the results of the building energy consumption prediction model, uses MAPE and RMSE indexes to evaluate the accuracy of the prediction results of the model, and uses the prediction time and input parameter dimensions to evaluate the time cost of the prediction model. Then, using the three building energy consumption prediction models based on machine learning algorithm established above, the prediction of energy consumption of four types of public buildings in different seasons is completed, and the prediction results are evaluated and analyzed. According to the prediction results and the requirements of related work on the accuracy of building energy consumption prediction model, the adaptation relationship between different types of buildings and different machine learning algorithm prediction models is summarized.

Intelligent Power Management Models for Buildings: A Comparative Analysis

“…At the other hand, deep learning algorithms are becoming increasingly popular for managing building power usage, which is based on correct forecasting of building energy usage, which is an essential component of building energy efficiency and emission reduction. Wang [21] presented assessment indexes of the results of the building energy consumption prediction model. They used Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) indexes to assess the accuracy of the model's prediction results, and using the prediction time and input parameter dimensions to evaluate the prediction model's time cost.…”

Predicting Energy Consumption in Residential Buildings Using Advanced Machine Learning Algorithms

“…Energies 2023, 16, 3748 2 of 23 Energy consumption prediction plays an important role in enabling buildings' energy management and control, energy strategy development, and quantification of energy saving potential [4]. In general, there are two types of models used for predicting the building energy consumption: physical models and data-driven models.…”

“…ML-based methods, as a data-driven approach, do not require detailed physical information about the buildings, their energy infrastructure, or their surroundings. Meanwhile, a new class of ML-based methods called deep learning (DL) has gained widespread attention and application in the field of building energy consumption prediction [15,16].…”

Estimation of biomass energy consumption in rural China

“…于使用更为清洁的能源 [11] ， 因此， 选取的代表性论文 调查的是发达地区还是贫困地区将会对总量核算 产生显著影响。②通过估算能源需求函数测算全 国生物质能用能总量。由于数据的不可得性和方 法的不确定性， 这方面的研究数量很少。早在 20 世 纪 90 年代， Sun [12] 基于能源需求函数估算了 1990 年 中国农村实际能源消费情况。他认为， 同一地区人 均能源使用量主要取决于温度和收入水平这两个 变量， 因此， 农村人均能源使用量可以通过已知的 城镇人均能源使用量推导出来。Sun 以城镇人均用 能来反推农村人均用能， 忽略了城乡间限制用能的 不仅是收入差异， 能源可达性差异也是一个重要因 素。尽管 Sun 的分析存在偏误， 但是这种通过构建 人均能源需求函数来间接推断用能总量的方法给 后来生物质能的核算带来了启发。Tao 等 [13] 采用上 述研究思路， 基于一个全国典型调查的 4 年回忆数 据估算了 1992-2012 年中国农村家庭生物质能用 能情况。Peng 等 [14] 预测。Wang 等 [16] 建立 3 种基于机器学习算法的建 筑能耗预测模型， 并利用平均绝对百分误差 (MAP) 和均方根误差 (RMSE) 指标评价模型预测结果的准 确性。Tian [17] [21] 和 线 性 参 数 化 动 态 趋 势 [22]…”