Operation Of Building Energy Systems Research Articles

Active learning concerning sampling cost for enhancing AI-enabled building energy system modeling

Machine learning is widely recognized as a promising data-driven modeling technique for the model-based control and optimization of building energy systems. However, the generalizability of data-driven models often faces significant challenges, as the available training data from building operations usually only covers a limited range of working conditions. Active learning can proactively test unseen and informative working conditions to enrich the training set by adding new data samples, leading to improved generalization performance of data-driven models. A novel distance and information density-based sample strategy is developed that accounts for the real-time status of building operation and outdoor environment. Based on Mahalanobis distance, this strategy determines the sampling value of an unlabeled sample (unseen working condition) by assessing its similarity to both the training samples and other unlabeled samples. As collecting sufficiently representative samples can be difficult, costly, and time-consuming, a distance-based sampling cost metric is proposed to compare the efficiency of different sampling methods, considering the detrimental effects of the actively sampling process on the normal operation of building energy systems. This paper presents a comprehensive and in-depth comparison of five active learning methods, including one incorporating the distance-based sampling strategy, by conducting data experiments on the data collected from the cooling towers of a real high-rise building. The results show that active learning can effectively identify informative data samples and improve the generalization performance of data-driven models. The research outcomes are valuable for enhancing AI-enabled data-driven modeling of building energy systems with substantial decreases in costs on data sampling.

Co-optimization of building energy systems with renewable generations combining active and passive energy-saving

Establishing clean and efficient building energy systems (BES) is an efficient path to promote the low-carbon energy transition to achieve the goal of carbon peak and carbon neutrality. To fully tap the energy saving potential of buildings, a co-optimization method combined active and passive energy-saving technologies is proposed for BES. The structures and characteristics of active and passive energy-saving means are modeled and analyzed. On this basis, a double-layer co-optimization model is built to optimize the planning and operation of BES separately. Furthermore, a carbon tax is introduced to establish the connection between active and passive means, and actual uncertainties of source-load are considered through the probabilistic scenario generation and interval linear programming approach. Case studies on the BES in Xiong’an New Area, China show that the proposed co-optimization method saves about 2.2%–3.4% costs than considering only the active energy-saving. Analysis of forecast errors for different scenarios reveals planning options and detailed costs under different levels of uncertainty.

Adaptive Optimization Design of Building Energy System for Smart Elderly Care Community Based on Deep Deterministic Policy Gradient

In smart elderly care communities, optimizing the design of building energy systems is crucial for improving the quality of life and health of the elderly. This study pioneers an innovative adaptive optimization design methodology for building energy systems by harnessing the cutting-edge capabilities of deep reinforcement learning. This avant-garde method initially involves modeling a myriad of energy equipment embedded within the energy ecosystem of smart elderly care community buildings, thereby extracting their energy computation formulae. In a groundbreaking progression, this study ingeniously employs the actor–critic (AC) algorithm to refine the deep deterministic policy gradient (DDPG) algorithm. The enhanced DDPG algorithm is then adeptly wielded to perform adaptive optimization of the operational states within the energy system of a smart retirement community building, signifying a trailblazing approach in this realm. Simulation experiments indicate that the proposed method has better stability and convergence compared to traditional deep Q-learning algorithms. When the environmental interaction coefficient and learning ratio is 4, the improved DDPG algorithm under the AC framework can converge after 60 iterations. The stable reward value in the convergence state is −996. When the scheduling cycle of the energy system is between 0:00 and 8:00, the photovoltaic output of the system optimized by the DDPG algorithm is 0. The wind power output fluctuates within 50 kW. This study realizes efficient operation, energy saving, and emission reduction in building energy systems in smart elderly care communities and provides new ideas and methods for research in this field. It also provides an important reference for the design and operation of building energy systems in smart elderly care communities.

Sustainable Operation of Active Distribution Networks

The present and future conditions in the energy market impose extremely high standards to the operation of building energy systems. Moreover, distribution networks face new operational and technical challenges as a result of the rapid penetration of renewable energy sources (RES) and other forms of distributed generation. Consequently, active distribution networks (ADNs) will play a crucial role in the exploitation of smart building prosumers, smart grids, and RES. In this paper, an optimization method for the sustainable operation of active distribution networks hosting smart residential building prosumers, plug-in electric vehicle (PEV) aggregators, and RES was developed. The thermal and electrical loads of the residential buildings were modeled in detail and an aggregation method was implemented to the hosted PEVs. Moreover, smart power dispatch techniques were applied at each building prosumer and PEV aggregator hosted by the active distribution network. Simultaneously, all the operational limitations of the active distribution network, building energy systems, and the hosted PEVs were satisfied. The constrained optimal power flow (OPF) algorithm was exploited to keep the voltages of the hosting distribution network between the permissible bounds. A significant operation cost reduction of 17% was achieved. The developed models were verified through detailed simulation results.

Active Optimization of Chilled Water Pump Running Number: Engineering Practice Validation

To realize building energy conservation, appropriate operation of building energy systems is necessary. A chilled water pump, an essential component for chilled water transportation in building cooling systems, consumes substantial energy. Hence, its operation should be optimized. Previous studies on optimal pump control mostly focused on pump speed/frequency control, while the control of pump running number is usually too passive to realize energy-saving objectives. Moreover, existing relevant studies have some disadvantages, such as (1) too complex a workflow for maintenance; (2) dependence on accurate system performance models that take substantial data and labor to establish; and (3) high requirements on monitoring and sensors. To tackle those problems, this article proposes a simple, feasible approach to optimize the running number (on/off status) of chilled water pumps for building energy conservation. The proposed method is merely based on similarity/affinity laws and pump performance curves feasible for engineering practices. It has been implemented on a real cooling system in a battery factory. Our results suggest that: (1) based on similarity/affinity laws and pump performance curves, the estimation of potential targeted pump working points is accurate enough for optimal control (the flow rate estimation error is less than 2%, the frequency estimation error is less than 1 Hz); (2) the energy-saving effect of this control method is evident (20% of pump energy is saved by the proposed method compared to the former control logic); (3) the water grid operation condition is maintained well: cooling supply is not sacrificed by the control intervention (compared to the working condition before the intervention, grid pressure difference changed by 1.4%, flow rate changed by 2.6%). Regarding the low preconditions, simple workflow, and acceptable energy-saving performance of the proposed method, it is suitable for energy conservation in building cooling systems.

Model predictive control for demand flexibility: Real-world operation of a commercial building with photovoltaic and battery systems

Hundreds of studies have investigated Model Predictive Control (MPC) for the optimal operation of building energy systems in the past two decades. However, MPC field tests are still uncommon, especially for small- and medium-sized commercial buildings and for buildings integrated with onsite renewables. This paper describes the implementation and the long-term performance evaluation of an MPC controller in a small commercial building equipped with behind-the-meter photovoltaics and electrochemical batteries. MPC controls space conditioning, commercial refrigeration, and the battery system. We tested two types of demand flexibility applications in the field: electricity bill minimization under time-of-use tariffs and responses to grid flexibility events. Results show that the proposed controller achieves 12% of annual electricity cost savings and 34% peak demand reduction against the baseline, while respecting thermal comfort and food safety. The field tests also demonstrate the ability of the MPC controller to provide a multitude of grid services including real-time pricing, demand limiting, load shedding, load shifting, and load tracking, using the same optimization framework.

Comparative study of supervised algorithms for topology detection of sensor networks in building energy systems

Optimizing the operation of building energy systems holds great potential to reduce energy consumption in buildings. However, this requires detailed system information, such as the relationship of sensor data. Automatic detection of this information requires monitoring data from buildings, which is rarely available in the needed quality for automatic assignment. This study bases on 200 weeks of data collected from eight temperature sensors of a heat pump and a heat exchanger in 5-min samples. We use this data to auto-generate grey-box models to extend the data set with 500 weeks of simulated data. We train six supervised deep learning algorithms with all the data to test whether detecting connections is possible. The maximum F1 score of 94.9% compared to real-based results with a maximum of 34.2%, which is over 60% better. The advantage of the proposed approach is its independence from the low availability of real data.

An occupant-centric control framework for balancing comfort, energy use and hygiene in hot water systems: A model-free reinforcement learning approach

Occupants’ behavior is a major source of uncertainty for the optimal operation of building energy systems. The highly stochastic hot water use behavior of occupants has led to conservative operational strategies for hot water systems, that try to ensure occupants’ comfort by following energy-intensive operational approaches. Intending to integrate the occupants’ behavior into hot water systems control, this study proposes a control framework based on Reinforcement Learning, which can learn the stochastic occupants' behavior and make a balance between opposing objectives of water hygiene, comfort, and energy use. A model-free approach is implemented to ensure transferability. To achieve fast convergence on the target house while being model-free, this study proposes an offline training procedure integrating a stochastic hot water use model to mimic the hot water use behavior of occupants. The proposed framework is then evaluated using an actual hot water use and weather dataset collected over 29 weeks from a residential house in Switzerland. The performance of the proposed control framework is compared to the conventional rule-based controller as the common practice in hot water systems. While the hot water use dataset has been collected during the COVID-19 pandemic, with an abnormal schedule of occupants, results indicate that the proposed control framework could successfully learn and adapt to the occupants' behavior and achieve 23.8% of energy saving, while maintaining the occupants' comfort and water hygiene. The adaptive nature of the proposed control framework shows significant potential in reducing the discrepancy between supply and demand in hot water systems.

A new workflow for detailed urban scale building energy modeling using spatial joining of attributes for archetype selection

Cities play an essential role in energy consumption and its environmental impacts. Urban Building Energy Modeling (UBEM) can help optimize the built environment's energy efficiency and improve the design and operation of building energy systems. In order to develop UBEM, individual buildings' characteristics such as constructions, internal loads, energy systems, etc., are required. To develop a comprehensive urban building energy model requires detailed 3D urban building geometry information, comprehensive building attribute libraries and a detailed archetype selection to automatically assign parameters to the building construction and usage. Most of the already developed tools do not take full advantage of external data sources of building characteristics with different formats and integrate them into the UBEM workflow. This study introduces a workflow to automatically extract, collect, and pre-process the energy-related parameters from open-source data to enrich the UBEM using spatial joining of attributes and detailed archetype selection. Two different 3D urban models (low and high resolution) are proposed to be used for urban building energy simulation. The workflow using the high-resolution model is demonstrated by applying it to the downtown Montreal buildings as a Canadian case study. A novel method for assigning the building's attributes to the building surfaces and thermal zones is developed, which is based on a detailed and automatic archetype selection. The archetype-selected data and other required information for urban building energy demand calculation are fed into EnergyPlus by introducing a hierarchical concept. The high-resolution enriched UBEM is calibrated using monthly measured data of a reference building, which resulted in an acceptable root mean square error. The method was then applied to the whole district, and it could be shown that ventilation and infiltration rates have the highest impact on energy demand. This study shows that using high-resolution UBEM allows detailed urban building energy analysis, which helps decision-makers to better understand their built environment.

Comparison of machine-learning models for predicting short-term building heating load using operational parameters

Short-term building energy consumption prediction is of great significance to the optimal operation of building energy systems and conservation. Machine-learning models are widely used due to their high prediction accuracy and efficiency in dealing with high-dimensional nonlinear problems. To compare the performance of different machine-learning models in building energy consumption prediction, this paper analyzes 15 machine-learning models, including a multi-layer perception, a radials basis function neural network, a generalized regression neural network, an extreme learning machine, a support vector machine, a least-square support vector machine, a Gaussian process regression, a regression tree, a model five tree, a random forest, a gradient boosting decision tree, an extreme gradient boosting tree, a light gradient boosting machine, a categorical gradient boosting tree and a multi-adaptive regression spline, from the aspects of model prediction accuracy, model stability (over-fitting) and calculation speed. The operation parameters determined by ReliefF algorithm were used as input parameters. The results showed that the prediction accuracy of all models is higher in the training phases, with R2 values greater than 0.90, while the prediction accuracy in testing phases was much lower. In terms of prediction accuracy and model stability, the Gaussian process regression model had the best overall performance among the 15 models, while the support vector machine had the faster calculation speed with acceptable prediction accuracy. For small datasets, the Gaussian process regression model is recommended, and the support vector machine should be preferred for large datasets. The results of this paper can provide a basis for model selection and the establishment of combined models for predicting building energy consumption.

Long term performance monitoring and KPIs’ evaluation of Aquifer Thermal Energy Storage system in Esker formation: Case study in Stockholm

The majority of Aquifer Thermal Energy Storage (ATES) systems studies have been conducted in aquifer systems located in large sand aquifers. Esker formation present a more challenging geometrical complexity compared to typical sand aquifers. This study aims to conduct comprehensive and long term performance evaluation of doublet type ATES system in esker geological formation in Stockholm, Sweden. The total heating and cooling used from the ATES are 673 MWh and 743 MWh respectively during the first 3 annual storage cycles of operation. The licensed total amount of water extraction and injection is 50 liters per second with undisturbed groundwater temperature of 9.5°C. Over the first three storage cycles, the average injection and extraction temperatures for the warm side are 13.3°C and 12.1°C, and for the cold side 7.6°C and 10.5°C. The average temperature differences across the main heat exchanger from the ATES side are 4.5 K during winter and 2.8 K during summer which is 4-5 degrees lower than the optimum value. The average thermal recovery efficiency over the first 3 storage cycles were 47 % and 60 % for warm and cold storages respectively. The data analysis indicated annual energy and hydraulic imbalances which results into undesirable thermal breakthrough between the warm and cold side of the aquifer. This was mainly due to suboptimal operation of the building energy system which led to insufficient heat recovery from the warm side, and subsequently insufficient cold injection in the cold wells, despite the building heating demand and the available suitable temperatures in the ATES. The cause of the suboptimal operation is the oversizing of the heat pumps which were designed to be coupled to larger thermal loads as compared to the ones in the final system implementation. As a result, the heat pumps could not be operated during small-medium loads. Additionally, the paper discusses the limitations of currently used energy and thermal key performance indicators (KPI) for ATES and propose an additional thermal KPI named heat exchanger efficiency balance (βHEX) that connects and evaluate the optimum operational point of temperature differences from both the building and ATES prospective. In addition to ATES energy and hydraulic KPIs, βHEX can contribute in providing more complete picture on the ATES-building interaction performance as well as highlights if the losses in energy recovery from ATES are due to the subsurface processes or building energy system operation which has been proven to be critical for the optimum ATES performance.

Application of data-driven methods for energy system modelling demonstrated on an adaptive cooling supply system

The efficient and sustainable operation of building energy systems is playing an increasingly important role in most industrialized countries. At the same time, building energy systems are becoming increasingly complex; fault-free and optimal operation, under dynamic boundary conditions, is becoming more and more challenging. There are many approaches in research to address the optimal control problem of building energy systems, such as Rule-based Control, Model Predictive Control, or Adaptive Control. However, most methods rely on models of the system dynamics with high prediction accuracies. This is especially the case in Model Predictive Control, where the model is part of a continuously executed optimization problem; but models are also required when it comes to the optimal design of Rule-based Controllers, the safe pre-training of Adaptive Controllers, or model-based fault detection. A limiting factor for the manual development of physical models, for building energy systems, are the low monetary incentives for engineering services, due to the low energy prices in most countries. In addition, the creation of such models is time-consuming and error-prone, even for domain experts. Another weakness is that changes in the system dynamics are not automatically adapted within the models. These challenges are contrasted by an increasing availability of monitoring-data and computational power in recent years; with machine-learning algorithms, these resources are used in numerous application areas to achieve very promising results. Machine-learning methods can help to obtain data-driven, self-calibrating models, which can be learned from monitoring-data. In this paper, we apply methods for automated data-driven model generation. We demonstrate how machine-learning algorithms together with structured hyper-parameter tuning can be used to model individual subsystems as well as a complete energy supply system. To represent the dynamics of the supply system, it is first decomposed into simple functional relationships, which are aggregated into the overall system after training of the comparatively simple subsystem models. We evaluate the accuracy of the data-driven subsystem models using established metrics for the evaluation of regression models, namely the R2-score and the RMSE. The considered system is integrated into a district cooling network and consists of two compression chillers and an ice storage unit. Our investigations show that the dynamics of the subsystems can be learned with high accuracies, depending on the operation mode and the selected features. The prediction of the power demand of the compression chillers is learned with R2-scores between 0.94 and 0.99 and RMSE values between 2.02 kW and 3.51 kW. Also, the prediction of the percentage of ice formation within the ice storage is learned accurately with a R2-score of 1 and RMSE values between 0.08 % and 0.72 %. The dynamics of the aggregated system also show plausible behavior and can thus be used in future work. This work is part of an ongoing research project with the aim to optimize the operation of the entire campus cooling energy supply system. Our results show that, if detailed monitoring-data are available, data-driven modelling represents a viable alternative to the labor-intensive physical modelling approach. Furthermore, we emphasize the importance of structured hyper-parameter tuning, discuss the specifics of different machine-learning algorithms, and elaborate on possible future developments in this research area.

Short-term modeling of hybrid geothermal systems for Model Predictive Control

Model Predictive Control (MPC) has shown significant energy savings potential in the operation of building energy systems, yet it needs accurate and simple models for optimization. In hybrid geothermal systems the source-side temperatures affect the system efficiency and its operational feasibility. Since the ground dynamics are rather slow, simplifications such as considering a constant coefficient of performance (COP) are made. We evaluate the added value of including a short-term dynamic borefield model to the controller. Simulations are performed in a heating-dominated building equipped with a hybrid geothermal system for two winter weeks. We consider 4 different modeling strategies where the formulation of the COP and the return fluid temperature from the borefield is varied in complexity. Results show that using a constant COP results in a bang-bang behavior of the heat pump, while with an accurate prediction of the COP the operation is smoother, saving 0.46%, 1.86% and 2.71% for low, average and high electricity-to-gas price ratios respectively. Including a short-term borefield model avoids shutting down the heat pump due to safety constraints which saves up to 8.12% more money while the use of the ground-source is quintupled. Despite reducing the optimization iteration number by almost 18%, simulation time is increased.

Exergy-based control strategies for the efficient operation of building energy systems

Abstract This article addresses the merits of exergy-based control strategies in comparison to energy-based ones in terms of increasing the energetic efficiency of a building and/or decreasing the operating costs of Heating, Ventilation and Air Conditioning (HVAC) systems. In this study, a dynamic exergy model for building energy systems is demonstrated to calculate exergy destruction which is a true measure of thermodynamic inefficiencies in a system. The exergy-based control strategies minimize exergy destruction obtained from the building exergy model while satisfying thermal comfort constraints. In this way, HVAC systems operate in a low-exergy fashion. The results of this study show that the implementation of exergy-based control strategies reduces the quality mismatch between energy supply and demand, and therefore, increases the sustainability of building energy systems. To prove the practicability of the idea, application of exergy-based control strategies in different types of case studies is investigated. The first case study deals with the design of optimal local controllers for the end-users without considering the entire energy supply chain. It is shown that the total operating cost of the system can be decreased by 13% through the implementation of an exergy-based control strategy. The second case study proposes an exergy-based control algorithm that, in addition to the end-users, also considers the upstream components and sub-systems in the energy supply chain. This control algorithm has been tested in a part of the heating system in the main building of the E.ON Energy Research Center (ERC), and the results shows that the proposed control strategy is sufficiently fast and the mass flow rates inside the consumer circuits are relatively stable. The third case study demonstrates a large-scale application, in which an Exergy-based Linear Model Predictive Controller (ExLiMPC) is implemented in a dynamic model representing the working principles of the HVAC and control systems of the main building of the E.ON ERC. A comparison between the default controller and the ExLiMPC shows that the ExLiMPC is able to decrease the overall energy demand of the building by 23.1%.

Comparison of clustering algorithms for the selection of typical demand days for energy system synthesis

Abstract The optimal design, sizing and operation of building energy systems is a complex problem due to the variety of available generation and storage devices as well as the high-resolution input data required for considering seasonal and intraday fluctuations in the thermal and electrical loads as well as renewable supply. A common measure to reduce the problem's size and complexity is to cluster the demands into representative periods. There exist many different algorithms for the clustering, but to the best of our knowledge, no comparison has been made that illustrates which algorithms are the most appropriate for such problems. Therefore, this paper compares six aggregation methods for reducing full year input data to typical demand days for energy system synthesis. We consider seasonal and monthly classification as well as sophisticated clustering methods such as k-centers, k-means, k-medians and k-medoids for aggregating the heat and electricity demand as well as solar irradiation onto the roof of a single-family house and an apartment building. The results show that all clustering methods are able to determine energy systems that are close to the optimal system, however their demand related costs are approximated best and most reliably with k-medoids.

System Approach for Building Energy Conservation

Energy use in residential and commercial buildings and towers represents more than 30% of energy consumption. The increase in number of buildings and towers in most of the major cities worldwide led to several initiatives for energy conservation programs with the main objective to achieve energy savings. Most energy strategies include energy conservation beside the increase in the penetration of renewable energy technologies. This paper shows business model and engineering design framework for practical implementation of energy conservation in buildings. Key performance indicators are modeled and used to evaluate energy conservation strategies and energy supply scenarios as part of the design and operation of building energy systems. The proposed system approach shows effective management of building energy knowledge on the basis of Energy Semantic Networks (ESN), which supports the simulation, evaluation, and optimization of several building energy conservation scenarios. Case study hotel is used to illustrate the proposed building energy conservation framework.