Machine Learning-based Energy Research Articles

Evaluating missing data handling methods for developing building energy benchmarking models

This study explored methods for handling missing data in the development of machine learning-based energy benchmarking models, assessing their training time, performance, and variance. Unlike the common assumption of missing completely at random, this study adopted a missing at random (MAR) perspective, which is more appropriate for building data. We compared the inherent missing data handling method of extreme gradient boosting (XGBoost) with the Median, k-nearest neighbors (KNN), and classification and regression trees (CART) methods, alongside Shapley additive explanation (SHAP) method for model interpretability. The findings indicate that, despite its computational demands, the CART method most accurately mirrors the original data distribution, thereby enhancing model performance and stability. The KNN method is effective, while the XGBoost method is viable under computational time constraints. This work highlights the importance of reliable test data for performing accurate evaluations of imputation methods. These results offer guidelines for the selection of imputation methods in model development, contributing to the improved accuracy of energy benchmarking models. The MAR-based approach for missing data analysis holds promise for future research on building energy data, providing crucial insights for accurate energy benchmark model performance assessments.

Machine learning-based energy management and power forecasting in grid-connected microgrids with multiple distributed energy sources

The growing integration of renewable energy sources into grid-connected microgrids has created new challenges in power generation forecasting and energy management. This paper explores the use of advanced machine learning algorithms, specifically Support Vector Regression (SVR), to enhance the efficiency and reliability of these systems. The proposed SVR algorithm leverages comprehensive historical energy production data, detailed weather patterns, and dynamic grid conditions to accurately forecast power generation. Our model demonstrated significantly lower error metrics compared to traditional linear regression models, achieving a Mean Squared Error of 2.002 for solar PV and 3.059 for wind power forecasting. The Mean Absolute Error was reduced to 0.547 for solar PV and 0.825 for wind scenarios, and the Root Mean Squared Error (RMSE) was 1.415 for solar PV and 1.749 for wind power, showcasing the model’s superior accuracy. Enhanced predictive accuracy directly contributes to optimized resource allocation, enabling more precise control of energy generation schedules and reducing the reliance on external power sources. The application of our SVR model resulted in an 8.4% reduction in overall operating costs, highlighting its effectiveness in improving energy management efficiency. Furthermore, the system’s ability to predict fluctuations in energy output allowed for adaptive real-time energy management, reducing grid stress and enhancing system stability. This approach led to a 10% improvement in the balance between supply and demand, a 15% reduction in peak load demand, and a 12% increase in the utilization of renewable energy sources. Our approach enhances grid stability by better balancing supply and demand, mitigating the variability and intermittency of renewable energy sources. These advancements promote a more sustainable integration of renewable energy into the microgrid, contributing to a cleaner, more resilient, and efficient energy infrastructure. The findings of this research provide valuable insights into the development of intelligent energy systems capable of adapting to changing conditions, paving the way for future innovations in energy management. Additionally, this work underscores the potential of machine learning to revolutionize energy management practices by providing more accurate, reliable, and cost-effective solutions for integrating renewable energy into existing grid infrastructures.

Machine Learning-Based Energy Optimization and Anomaly Detection for Heterogeneous Wireless Sensor Network

Machine Learning-Based Energy Optimization and Anomaly Detection for Heterogeneous Wireless Sensor Network

Predicting the PCM-incorporated building's performance using optimized linear kernel and tree-based machine learning methods

The devising of a precise machine learning-based energy consumption prediction model holds significant importance for taking effective decisions during the early stages of phase change material (PCM) incorporated building design to reduce energy consumption. Few researchers have developed prediction models for estimating the consumption of energy in PCM incorporated buildings. However, there is a need to develop the best-performing machine learning-based prediction model, which is less complex, involve a lower number of hyperparameters, and has a greater ability to generalize hidden patterns among the dependent and independent variables. To address the above shortcomings, the linear kernel and tree model-based prediction models were formulated for PCM-incorporated buildings located in eight cities of subtropical highland climate, considering the variations in their hyperparameters. The evaluation and validation of the formulated models for prediction were performed utilizing several statistical metrics. Test results substantiated that the ensemble-boosted tree-based prediction model (EBT20) exhibited superior efficacy in estimating the energy consumption for PCM-integrated building, having an average R2 > 0.93, NMBE <4 %, and CV-RMSE <8 %. The developed model showed less complexity and better generalization ability at the optimized values of ensemble boosted tree hyperparameters, which are as follows: minimum leaf size = 32, number of learners = 99, and learning rate = 0.1. From comprehensive evaluation conducted to evaluate the interpretability of the prediction model, it was found that the building orientation and PCMs melting temperature are the most influential parameters for achieving energy savings of up to 33 % in the selected climate zone.

Machine learning-Based Energy Efficient and Enhancing Communication Reliability for MANETs of Balanced Less Loss Routing Protocol

The aim of the presented research was the utilization of machine learning methods, for example, SOM, MARL, and DQN, to promote the increase of energy efficiency and communication reliability in MANET. For the purpose of the research conduction, 10 trials of the experiment were carried out with the view to establish the performance of the proposed approaches from various perspectives. DQN demonstrated superior performance throughout all experiment trials as compared to both SOM and MARL. The model recorded an average energy efficiency of 95%, indicating that it was highly successful in optimizing routing strategies and communication policies. Furthermore, the average packet delivery ratio was shown to be 96%, meaning that DQN provided guarantees of timely and reliable data exchange across the MANET infrastructure. Finally, the average delay was determined to be from 4 ms to 9 ms, evidencing the quick delivery of packets with little temporal latency. The results obtained demonstrate that DQN is able to alleviate the challenges associated with the energy efficiency and communication reliability of MANETs. Notably, deep reinforcement learning with DQN appears to offer viable solutions for more energy-efficient routing, minimized energy consumption in these networks, and improvement to their communication reliability. Thus, the study under consideration has contributed to the development of the existing knowledge as it has expanded the existing understanding of the fact that machine learning, in general, and DQN, in particular, can be utilized to optimize the operation of MANETs.

Machine learning-based energy monitoring method applied to the HVAC systems electricity demand of an Italian healthcare facility

The buildings energy consumption is a great part of Europe's overall energy demand. The development of diagnostic methods capable of promptly alerting users in case of issues (e.g. mild and progressive decrease in systems components performance) is crucial for the smart management of buildings. Machine learning-based building energy monitoring is a reliable approach for identifying subtle anomalies in the building energy demand behaviour. This study presents the application of a systematic procedure to develop a reliable monitoring method based on machine learning predictive models, ensuring minimal user knowledge requirements. The proposed method applied to the electricity demand of various components of the heating, ventilation and air conditioning system of a real Italian healthcare facility. The obtained models are exploited to apply the building energy monitoring method, assessing its capability to highlight mild changes in building energy demand behaviour. Considering that its application on specific system components implies an increased technical and economic effort to carry out data collection, the present work is aimed at assessing the benefits of such applications. Because of its high reproducibility and relatively simple integration into centralized building energy management systems, the proposed method offers a practical solution to enhance the smart management of building energy systems.

A Comparative Analysis of Machine Learning-Based Energy Baseline Models across Multiple Building Types

Building energy baseline models, particularly machine learning-based models, are a core aspect in the evaluation of building energy performance to identify inefficient energy consumption behavior. In smart city design, energy planners and decision makers require comprehensive information on energy consumption across diverse building types as well as comparisons between different types of buildings. However, there is no comprehensive study of baseline modeling across the main building types to help identify factors that influence the performance of different machine learning algorithms for baseline modeling. Therefore, the goal of this paper is to review and analyze energy consumption behavior and evaluate the prediction performance and interpretability of machine learning-based baseline modeling techniques across major building types. The results have shown that the Extreme Gradient Boosting Machine (XGBoost) model is the most accurate baseline modeling method for all building types. Time-related factors, especially the week of the year and the day of the week, have the most impact on energy consumption across all building types. This study is presented as a useful resource for smart city energy managers to help in choosing and setting up appropriate methodologies for better operational effectiveness and efficiencies when designing and planning smart energy systems.

A comparative study of the machine learning-based energy management system for hydrogen fuel cell electric vehicles

The demand for better energy technologies has sparked research and development of electric and hybrid vehicles. Due to their clean, sustainable, and high energy density, fuel cell vehicles have begun to stand out above the rest. Therefore, fuel cell hybrid vehicles can compete with internal combustion engine-powered vehicles in the future. However, fuel cells face obstacles, including slow dynamics that necessitate managing their operation together favorably. To reduce an HEV's operational costs, this study analyzes the HEV energy management issue utilizing machine learning approaches, particularly reinforcement learning. This paper aims to comprehensively review the existing work on a couple of machine-learning-based energy management systems for an electric vehicle run by hydrogen fuel cell, it can be concluded that progress was evident when the Q-learning-based algorithm was utilized towards lowering the SOC battery variation of about 0.7 per unit which was the primary task, while a Deep Deterministic Policy Gradient (DDPG) based energy management system (EMS) starts operating the fuel cell at a higher efficiency rate comparatively while using the battery.

Development of Machine Learning-Based Energy Management Agent to Control Fine Dust Concentration in Railway Stations

Development of Machine Learning-Based Energy Management Agent to Control Fine Dust Concentration in Railway Stations

Soft actor-critic-based EMS design for dual motor battery electric bus

Thanks to the outstanding adaptability and relatively simple design process, machine learning-based energy management strategies (EMSs) show their superiority in reducing the energy consumption for multi-power powertrains. Given the popularity of distributed-drive in battery electric vehicles (BEVs), this study selects a dual-motor four-speed electric bus to investigate the proposed soft actor-critic (SAC)-based EMS. Two improvements are made to the traditional SAC algorithm to meet the special requirements of EMS in a distributed-drive electric bus in this study. Firstly, the introduced combination of Gumbel-SoftMax and actor-network allows the SAC agents to explore the hybrid action space (discrete operating modes and continuous torque distribution coefficients). Secondly, a heuristic rule-interposing action controller (HRIAC) is involved to reduce illogical exploration of SAC agents in searching for optimal power distributing ratio. Simulation results demonstrate that Gumbel-SoftMax facilitates agents' exploration and narrows the energy consumption gap between the proposed EMS and the global optimal EMS, meanwhile, HRIAC accelerates the convergence of agent training. The comparative results of proposed EMS performance in unknown driving cycles show that the proposed EMS outperforms other deep reinforcement learning (DRL)-based EMSs in adaptability, which is taken as a solid foundation for energy efficiency improvement of dual-motor electric bus in practice.

Towards a blockchain and machine learning-based framework for decentralised energy management

In most domestic buildings, gas and electricity are supplied by energy and utility companies through centralised energy systems. This often results in a high burden on central management systems and has adverse effects on energy prices. Blockchain-based peer-to-peer energy trading platforms can deliver strategic operation of decentralised multi-energy network among multiple domestic buildings to reduce global greenhouse gas emissions and address global climate change issues. However, prevailing blockchain-based energy trading platforms focused on system implementation for peer-to-peer electricity trading while lacking predictive control and energy scheduling optimisation. Therefore, this paper presents an integrated blockchain and machine learning-based energy management framework for multiple forms of energy (i.e., heat and electricity) allocation and transmission, among multiple domestic buildings. Machine learning is harnessed to predict day-ahead energy generation and consumption patterns of prosumers and consumers within the multi-energy network. The proposed blockchain and machine learning-based decentralised energy management framework will establish optimal and automated energy allocation among multiple energy users through peer-to-peer energy transactions. This approach focuses on energy-matching from both the supply and demand sides while encouraging direct energy trading between prosumers and consumers. The security and fairness of energy trading can also be enhanced by using smart contracts to strictly execute the energy trading and bill payment rules. A case study of 4 real-life domestic buildings is introduced to determine the economic and technical potential of the proposed framework. In comparison to prevailing approaches, a key benefit from the proposed approach is an improved computational load/failure of a single point, energy trading strategy, workload, and capital cost energy. Findings suggest that energy costs reduced between 7.60% and 25.41% for prosumer buildings and a fall of 5.40%-17.63% for consumer buildings. In practical applications, the proposed approach can involve a larger number of prosumer and consumer buildings within the community to decentralise multiple energy trading, thus significantly contributing to the reduction of greenhouse gas emissions and enhancing environmental sustainability.

Machine Learning-Based Energy Consumption Estimation of Wastewater Treatment Plants in Greece

Amidst a global discourse on energy resources, it is imperative to provide decision makers with a comprehensive overview of energy consumption (EC) associated with various projects, particularly wastewater treatment plants (WWTPs). Ensuring compliance with stringent effluent quality criteria in the treatment of municipal wastewater necessitates a substantial EC, representing a predominant factor contributing to the operational expenses incurred by WWTP. Machine learning (ML) techniques can contribute to the estimation of the WWTPs’ EC, which requires efficient and accurate data. This article uses data from several municipal WWTP projects in Greece, which are examined in order to produce EC estimation models. Data were first statistically analyzed, according to the context of project attributes and the context of EC, and correlation analysis identified the appropriate predictive project variables. Then, the attribute selection function in Waikato Environment for Knowledge Analysis 3.8.4 (WEKA 3.8.4) software emphasized the most effective subset of variables. The extracted variables from the combination of the correlation analysis and the WEKA attribute function were used as input neurons for the construction of neural network (NN) models, in the Fast Artificial Neural Network Tool 1.2 (FANN Tool 1.2). The optimum NN model resulted in a mean squared error (MSE) of 8.99899 × 10−5 and was based on treatment capacity, flow rate, influent load, and served population as its inputs. Notably, the research highlights the potential generalizability of these models in Greece and beyond the Greek context, offering valuable tools for stakeholders to inform decision making, allocate resources efficiently, and improve energy-efficient designs, resulting in cost savings and sustainability benefits.

Machine learning-based energy use prediction for the smart building energy management system

Smart building is a building development approach utilizing digital and communication technology to improve occupants' comfort inside the building and help increase energy usage efficiency in building operations. Despite its benefits, the smart building concept is still slowly adopted, particularly in developing countries. The advancement of computational techniques such as machine learning (ML) has helped building owners simulate and optimize various building performances in the building design process more accurately. Therefore, this study aims to assist energy efficiency design strategies in a building by identifying the features of the smart building characteristics that can potentially foster building energy efficiency. Furthermore, an ML model based on the features identified is then developed to predict the level of energy use. K-Nearest Neighbor (k-NN) algorithm is employed to develop the model with the openly accessible smart building energy usage datasets from Chulalongkorn University Building Energy Management System (CU-BEMS) as the training and testing datasets. The validation result shows that the predictive model has an average relative error value of 17.76%. The energy efficiency levels obtained from applying identified features range from 34.5% to 45.3%, depending on the reviewed floor. This paper also proposed the dashboard interface design for ML-based smart building energy management.

Machine learning-based energy harvesting for wearable exoskeleton robots

Wearable exoskeleton robot can provide additional movement assistance for the wearer in many fields and enhance their movement ability. Reduce the degree of long-term exercise fatigue and avoid injury during exercise. However, due to the limitation of battery technology and battery capacity, it is difficult for exoskeleton robots to work continuously for a long time. Therefore, the energy management and optimization of wearable exoskeleton robot become an important way to break through the bottleneck of its future development. In order to optimize the energy management system of exoskeleton robot, an energy management control strategy based on machine learning and a SOC11SOC: State of Charge. value prediction model were proposed. Based on the structure of composite power supply, this paper selects Q-learning in machine learning to build the battery energy management strategy system, and introduces the time difference reinforcement learning algorithm. The experimental results show that the energy management optimization system can effectively shorten the response time of the robot system, reduce the prediction error value of SOC value, and provide more accurate electricity information for the management and control system. At the same time, the system in this paper shows good energy management control under different working conditions, and can realize dynamic energy management and improve energy utilization according to the actual power demand and power supply operation of the exoskeleton robot.

The application of machine learning-based energy management strategy in a multi-mode plug-in hybrid electric vehicle, part II: Deep deterministic policy gradient algorithm design for electric mode

Machine learning (ML)-based methods have attracted great attention in the multi-objective optimization problems, which is the key challenge in the energy management strategy (EMS) of the multi-power hybrid system. Our recently published research in this journal verified the effectiveness and feasibility of a Deep Deterministic Policy Gradient (DDPG)-based EMS in the charge-sustaining (CS) stage of a multi-mode plug-in hybrid vehicle (PHEV). However, the application of ML-based-EMS in the charge-depletion (CD) stage and the regenerative braking mode of PHEV are still missing. This study proposes a discrete-continuous hybrid actions-based hierarchical EMS to optimally distribute the dual-motor driving force in battery electric driving and regenerative braking. In the upper layer of EMS, DDPG is trained to learn the torque distribution principles of dual-motor operation to achieve better energy efficiency without losing dynamic performance. Meanwhile, the total recoverable braking torque is also determined by the upper layer EMS considering the braking demand, mechanical and electrical braking system conditions, vehicle safety, and the provisions of law. In the lower level of EMS, the driving mode is determined under the guidance of energy consumption optimization. The verified results show that the proposed EMS outperforms other deep reinforcement learning (DRL)-based hierarchical and non-hierarchical EMSs.

A Machine Learning-Based Energy Optimization System for Electric Vehicles

The growing demand for sustainable and eco-friendly transportation has led to the widespread adoption of electric vehicles (EVs). However, the limited driving range of EVs and the need for frequent recharging remain significant challenges. To address these challenges, researchers have proposed various energy optimization techniques, including machine learning-based approaches. In this paper, proposed method of Smart EV energy optimization systems for EVs. The system uses machine learning algorithms to analyze and learn from historical driving data, such as the driving patterns, road conditions, weather, and traffic. Based on this analysis, the system predicts the energy consumption of the EV and optimizes the energy usage to minimize energy waste and extend the driving range.

Empirical analysis of machine learning-based energy efficient cloud load balancing architectures: a quantitative perspective

Design of energy efficient load balancing models in cloud environments requires in-depth analysis of the cloud architecture and nature of requests served by the cloud. Depending upon these parameters, machine learning models are designed which aim at assigning best possible resource combination to serve the given tasks. This assignment varies w.r.t. multiple task and cloud parameters; which include task time, virtual machine (VM) performance, task deadline, energy consumption, etc. In order to perform this task, a wide variety of algorithms are developed by researchers cloud designers. Each of these algorithms aim at optimizing certain load balancing related parameters; for instance, a Genetic Algorithm (GA) designed for optimization of VM utilization might not consider task deadline before task allocation to the VMs. While, algorithms aimed at performing deadline aware load balancing might not provide effective cloud-to-task-mapping before allocation of tasks. Thus, it becomes difficult for researchers to select the best possible algorithms for their cloud deployment. In order to reduce this ambiguity, the underlying text compares different energy efficient cloud load balancing algorithms; and evaluates their performance in terms of computational complexity, and relative energy efficiency. This performance evaluation is further extended via inter architecture comparison; in order to evaluate the most optimum load balancer implementation for a given energy efficient application. Thus, after referring this text, researchers and cloud system designers will be able to select optimum algorithmic implementations for their given deployment. This will assist in reducing cloud deployment delay, and improving application specific load balancer performance.

Machine Learning-Based Control for Fuel Cell Hybrid Buses: From Average Load Power Prediction to Energy Management

In this work, a machine learning-based energy management system is developed using a long short-term memory (LSTM) network for fuel cell hybrid buses. The neural network implicitly learns the complex relationship between various factors and the optimal power control from massive data. The selection of the neural network inputs is inspired by the adaptive Pontryagin’s minimum principle (APMP) strategy. Since an estimated value of the global average fuel cell power is required in the machine learning-based energy management strategy (EMS), some global features of driving cycles are extracted and then applied in a feedforward neural network to predict the average fuel cell power appropriately. The effectiveness of the machine learning-based energy management, with the integration of the mechanism of estimating the average fuel cell power based on the forward neural network, is tested under two different driving cycles from the training environment, with comparisons to a commercially used rule-based strategy. Based on the simulation results, the learning-based strategy outperforms the rule-based strategy regarding the charge-sustaining mode conditions and fuel economy. Moreover, compared to the best offline hydrogen consumption, the machine learning-based strategy consumed 0.58% and 0.36% more than the best offline results for both driving cycles. In contrast, the rule-based strategy consumed 1.80% and 0.96% more than optimal offline results for the two driving cycles, respectively. Finally, simulations under battery and fuel cell aging conditions show that the fuel economy of the machine learning-based strategy experiences no performance degradation under components aging compared to offline strategies.

A Machine Learning-Based Energy Management Agent for Fine Dust Concentration Control in Railway Stations

This study developed a reinforcement learning-based energy management agent that controls the fine dust concentration by controlling facilities such as blowers and air conditioners to efficiently manage the fine dust concentration in the station. To this end, we formulated an optimization problem based on the Markov decision-making process and developed a model for predicting the concentration of fine dust in the station by training an artificial neural network (ANN) based on supervised learning to develop the transfer function. In addition to the prediction model, the optimal policy for controlling the blower and air conditioner according to the current state was obtained based on the ANN to which the Deep Q-Network (DQN) algorithm was applied. In the case study, it is confirmed that the ANN and DQN of the predictive model were trained based on the actual data of Nam-Gwangju Station to converge to the optimal policy. The comparison between the proposed method and conventional method shows that the proposed method can use less power consumption but achieved better performance on reducing fine dust concentration than the conventional method. In addition, by increasing the value of the ratio that represents the compensation due to the fine dust reduction, the learned agent achieved more reduction on the fine dust concentration by increasing the power consumption of the blower and air conditioner.

Application of Machine Learning-based Energy Use Forecasting for Inter-basin Water Transfer Project

Energy use forecasting is crucial in balancing the electricity supply and demand to reduce the uncertainty inherent in the inter-basin water transfer project. Energy use prediction supports the reliable water-energy supply and encourages cost-effective operation by improving generation scheduling. The objectives are to develop subsequent monthly energy use predictive models for the Mokelumne River Aqueduct in California, US. Partial objectives are to (a) compare the model performance of a baseline model (multiple linear regression (MLR)) to three machine learning-based models (random forest (RF), deep neural network (DNN), support vector regression (SVR)), (b) compare the model performance of the whole system to three subsystems (conveyance, treatment, distribution), and (c) conduct sensitivity analysis. We simulate a total of 64 cases (4 algorithms (MLR, RF, DNN, SVR) x 4 systems (whole, conveyance, treatment, distribution) x 4 scenarios (different combinations of independent variables). We concluded that the three machine learning algorithms showed better model performance than the baseline model as they reflected non-linear energy use characteristics for water transfer systems. Among the three machine learning algorithms, DNN models yielded higher model performance than RF and SVR models. Subsystems performed better than the whole system as the models more closely reflected the unique energy use characteristics of the subsystems. The best case was having water supply (t), water supply (t-1), precipitation (t), temperature (t), and population (y) as independent variables. These models can help water and energy utility managers to understand energy performance better and enhance the energy efficiency of their water transfer systems.