Intelligent Prediction Method of Building Energy Consumption Based on Deep Learning

Building energy consumption prediction plays an important role in realizing building energy conservation control. Limited by some external factors such as temperature, there are some problems in practical applications, such as complex operation and low prediction accuracy. Aiming at the problem of low prediction accuracy caused by poor timing of existing building energy consumption prediction methods, a building energy consumption prediction and analysis method based on the deep learning network is proposed in this paper. Before establishing the energy consumption prediction model, the building energy consumption data source is preprocessed and analyzed. Then, based on the Keras deep learning framework, an improved long short-term memory (ILSTM) prediction model is built to support the accurate analysis of the whole cycle of the prediction network. At the same time, the adaptive moment (Adam) estimation algorithm is used to update and optimize the weight parameters of the model to realize the adaptive and rapid update and matching of network parameters. The simulation experiment is based on the actual dataset collected by a university in Southwest China. The experimental results show that the evaluation indexes MAE and RMSE of the proposed method are 0.015 and 0.109, respectively, which are better than the comparison method. The simulation experiment proves that the proposed method is feasible.

A Digital Twin Architecture Model Applied with MLOps Techniques to Improve Short-Term Energy Consumption Prediction

Using extensive databases and known algorithms to predict short-term energy consumption comprises most computational solutions based on artificial intelligence today. State-of-the-art approaches validate their prediction models in offline environments that disregard automation, quality monitoring, and retraining challenges present in online scenarios. The existing demand response initiatives lack personalization, thus not engaging consumers. Obtaining specific and valuable recommendations is difficult for most digital platforms due to their solution pattern: extensive database, specialized algorithms, and using profiles with similar aspects. The challenges and present personalization tactics have been researched by adopting a digital twin model. This study creates a different approach by adding structural topology to build a new category of recommendation platform using the digital twin model with real-time data collected by IoT sensors to improve machine learning methods. A residential study case with 31 IoT smart meter and smart plug devices with 19-month data (measurements performed each second) validated Digital Twin MLOps architecture for personalized demand response suggestions based on online short-term energy consumption prediction.

A Novel CNC Milling Energy Consumption Prediction Method Based on Program Parsing and Parallel Neural Network

Accurate and rapid prediction of the energy consumption of CNC machining is an effective means to realize the lean management of CNC machine tools energy consumption as well as to achieve the sustainable development of the manufacturing industry. Aiming at the drawbacks of existing CNC milling energy consumption prediction methods in terms of efficiency and precision, a novel milling energy consumption prediction method based on program parsing and parallel neural network is proposed. Firstly, the relationship between CNC program and energy consumption of CNC machine tool is analyzed. Based on the structural characteristics of the CNC program, an automatic parsing algorithm for the CNC program is proposed. Moreover, based on the improved parallel neural network, the mapping relationship between the energy consumption parameters of each CNC instruction and the milling energy consumption is constructed. Finally, the proposed method is compared with the literature to verify the superiority of the proposed method in terms of prediction efficiency and accuracy, and the practicability of the method is verified through the case study. The proposed method lays the foundation for efficient and low-consumption process planning and energy efficiency improvement of machine tools and is conducive to the sustainable development of the environment.

Using Hybrid Machine Learning Methods to Predict and Improve the Energy Consumption Efficiency in Oil and Gas Fields

Oil and gas will remain essential to global economic development and prosperity for decades to come, and the oil and gas industry is an energy-intensive industry. Thus, enhancing energy efficiency for producing oil and gas in oil and gas companies is an important issue. The intelligent energy consumption prediction method with the ability to analyze energy consumption patterns and to identify targets for energy saving proved itself as an effective approach for energy efficiency in many industrial domains. Moreover, prediction of energy consumption enables managers to scientifically plan out the energy usage of energy production and to shift energy usage to off-peak periods. However, it still remains a challenging issue to some degree with the unpredictability and uncertainty caused by various energy consumption behaviors, and this phenomenon is becoming more obvious in the oil and gas company. To this end, in our work, we primarily discussed the forecasting of the energy consumption in the oil and gas company. Firstly, four different forecasting models, support vector machine, linear regression, extreme learning machine, and artificial neural network, were trained on the training dataset and then evaluated by the test dataset. Secondly, in order to enhance the energy consumption prediction accuracy, the combinations of all these four models were examined with the RMSE value by taking the average of two models’ outputs. The outcomes show that these four different models are able to predict energy consumption with good accuracy, but the hybrid model—artificial neural network and extreme learning machine—would present higher accuracy. In addition, the hybrid model is installed in the energy management system of the oil and gas industry to manage oil field energy consumption and improve the efficiency.