Operation Of Heating System Research Articles

Creating a labelled district heating data set: From anomaly detection towards fault detection

For an efficient operation of district heating systems, being able to detect anomalies and faults at an early stage is highly desirable. Here, data-driven machine learning methods can be a cornerstone, particularly for fault detection in district heating substations, where the availability of heat meter data keeps increasing. However, the creation of data sets suitable for training such machine learning models poses challenges to researchers and practitioners alike. To address this problem, we propose a systematic and domain-specific process for data set creation for fault detection in the form of practical guidelines. This process concretizes the data science and data mining cross-industry standard CRISP-DM for the district heating domain and focuses on the process steps of goal definition, data acquisition and understanding, and data curation. We aim to enable researchers and practitioners to create data sets for fault detection in the district heating domain and therefore also enable the creation or improvement of machine learning models in this domain. In addition, we propose a minimum viable feature set for fault detection in district heating networks with the goal of enabling better cooperation between researchers and easier transfer of the resulting machine learning models, to better proliferate new progress in the field.

A novel high-dimensional sensor calibration framework integrating thermodynamic laws in complex HVAC systems

Accurate calibration of sensors is critical for ensuring energy efficient operation of Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings. Due to the high dimensionality of sensor data and the complexity of multiple-fault scenarios, calibrating sensors in large and complex HVAC systems presents significant challenges. To address this issue, this study introduces a novel sensor calibration framework that integrates thermodynamic laws for high-dimensional sensor calibration in complex HVAC systems. The traditional calibration method heavily relies on accurate data, making it difficult to apply in practical engineering projects. The innovative aspect of our method lies in its integration of thermodynamic laws, such as mass balance and energy conservation, with sensor calibration framework. This approach enables the framework to handle high-dimensional sensor measurements effectively without any training data. We compared five optimization algorithms and applied them to a central cooling system in Hong Kong. The results demonstrated that the simulated annealing (SA) is the most robust for solving the calibration problem, even in scenarios with up to 21 faulty sensors, with the calibrated sensor accuracy meeting the standards for conventional chiller plant operations. This novel framework provides a robust and reliable solution for high-dimensional sensor calibration in large and complex HVAC systems, addressing the growing need for precise sensor calibration as the number of installed sensors increases.

Influence of the Building’s Thermal Insulation on Intermittent Heating Mode Efficiency

Abstract The results of mathematical modeling of a building’s thermal insulation influence on the efficiency of intermittent heating mode are presented. This work aim is to assess the influence of thermal insulation on the efficiency of using the intermittent heating mode for the educational building of the Odessa National Polytechnic University’s Heat Engineering Laboratory. The paper analyzes the factors related to improving the efficiency of the programmed heat supply mode. Modeling of the operating modes for heat supply system operated in intermittent heating mode is carried out. There was performed the mathematical modeling of the heating system operation modes for the most unfavorable climatic conditions at low outdoor temperatures, with respective system efficiency indicators obtaining. The potential of energy saving level for administrative, educational, and office buildings depending on the thickness of thermal insulation of external and internal walls is studied. Recommendations have been elaborated for the use of buildings thermal insulation to improve the efficiency of intermittent heating.

Resilient energy management of a multi-energy building under low-temperature district heating: A deep reinforcement learning approach

The corrective control of a building-level multi-energy system (MES) for emergency load shedding is essential to optimize the operating cost after contingency. For a Danish case, the heating devices in the building are connected to a developing low-temperature district heating (LTDH) system and operated under a heat market. Due to the coupling between the electrical power and heating system, an electricity outage can be propagated to the heating network, and heat prices as well as tariffs can impact the MES operating cost. In the previous studies, only electrical load shedding is modeled, while the impact of electricity outages on heating system operation and heat load control is ignored. On the other hand, the problem is traditionally solved by model-based optimization methods which are highly nonconvex leading to high computing complexity. Moreover, operating uncertainties can lead to infeasible solutions. To address these challenges, this paper proposes a deep reinforcement learning-based corrective control method for the resilient energy management of a building-level MES. In the method, the proximal policy optimization algorithm is applied, where multiple uncertainties, system dynamics, and operating constraints are considered. A case study of a real-life residential building connected to the LTDH system in Denmark is carried out, where electricity outages are simulated. The results verify the performance of the proposed method in achieving resilient energy management of the MES.

Multi-point temperature or humidity prediction for office building indoor environment based on CGC-BiLSTM deep neural network

The aim of this study is to predict the temperature or humidity changes at multiple relevant points in a building using a deep neural network architecture with multi-task learning to provide more reference information for the design and optimal operation of heating and ventilation systems. For this purpose, traditional multi-task prediction algorithm architecture is combined with Customized Gate Control and other neural networks to build deep neural network architectures for indoor environments with multi-point temperature or humidity prediction tasks. To test the prediction effectiveness of the architecture, a task of predicting temperature or humidity 24 h in advance was designed on a real office building indoor environment dataset, and the prediction results were compared with other single-task and multi-task prediction models. Two experimental conditions were designed for this study, one using the complete training set and the other reducing the training set at a certain point. Through the final prediction results, it is found that the multi-task prediction architecture used in this paper shows better or nearly optimal results compared to other prediction models under both working conditions. This study provides some reference value for the application of multi-task prediction algorithms to the task of predicting indoor environments in buildings.

Assessment of controlled assistance from e-bikes as a mitigation strategy for individual PM exposure

Abstract Background While promoting active mobility and outdoor activities can benefit health (HLT), it also increases Exposure (EXP) to air pollutants, such as particulate matter (PM), due to the increased ventilation rate (VR) under physical activity. Traditional assessments of individual (IND) PM EXP involve costly equipment inaccessible to the public, but real-time low-cost sensors (LCS) are now emerging. This study presents a proof of concept to demonstrate the use of LCS for examining the real-time IND respiratory dose deposited (RDD) to PM cycling across the Brescia province. Methods An e-bike was ridden 33 times between 2022 and 2023 wearing a LCS for PM concentration [PM] linked to a GPS. Respiratory dose deposited(RDD) was calculated for six different locations within each route based on experimental PM and various VR. Results The LCS allows for the study of the spatial and temporal variability of [PM], revealing a significant difference (p < 0.01) according to the heating system operation and no significant difference (p > 0.05) depending on the location. RDD increases with [PM] and VR. Real-time and integrated RDD is calculated for routes with high (> 50 µg/m3), medium (25 µg/m3), and low (<10 µg/m3) [PM2.5]. The e-bike assistance is activated when the WHO interim target 4 of [PM] is reached to reduce VR, which corresponds to a shift to a lower physical activity intensity. The RDD calculated using the e-bike assistance over the path reduces RDD by about 23% and 11% over the high and medium [PM], while it never activates for the low [PM]. Conclusions This study demonstrates that the use of LCS allows the estimation of IND RDD, and the implementation of mitigation strategies based on controlled assistance from e-bikes would enable the reduction of PM individual EXP. Key messages • The integration of HLT data from wearable and air quality LCS enables the promotion of active mobility and outdoor activities controlling the EXP to air pollutants. • Establishing generalized guidelines based on this mitigation strategies for individual exposure reduction may also inform policy recommendations for promoting active and green mobility.

Coordinated price-based control of modulating heat pumps for practical demand response and peak shaving in building clusters

With a high share of renewable energy in the power grid, it becomes increasingly difficult to ensure a continuous balance between power generation and consumption, thereby endangering grid stability. A substantial opportunity to address this challenge and align the heating demand with intermittent power production is offered by space heating and domestic hot water, which account for 80% of the energy consumption in buildings. Further research on the control of building clusters is required, where peak load management of multiple buildings can ensure grid stability during peak hours and contribute to avoiding power outages. In this paper, a rule-based controller is presented, called Extended Price Storage Control+ (EPSC+), for the practical and flexible operation of heating systems in a building cluster. Under dynamic pricing, the loads of electric heating devices for the provision of space heating and domestic hot water are shifted by EPSC+ while accounting for peak load constraints. The performance of EPSC+ is evaluated in a nine-week winter simulation study with a building cluster of ten buildings in Germany. For comparison, a hierarchical model predictive controller (MPC) and a hysteresis two-point controller are employed as benchmarks. Results close to those of MPC are achieved by EPSC+by reducing the median peak load by 38.8% and median electricity costs by 15% compared with the hysteresis controller. In contrast to MPC, EPSC+ does not require models, forecasts, or optimization and is computationally inexpensive, rendering it more attainable for real-world implementation.

Long-term climate-based sizing and economic assessment of air-water heat pumps for residential heating

This study presents a novel methodology for sizing air–water heat pumps (ASHP) for space heating and hot water supply in buildings. Utilizing long-term local climatic data, the developed tool determines the coefficient of performance (COP) and feasibility of ASHP. The sizing algorithm incorporates peak heat demand, unitary final energy demand, and seasonal heat demand across various detached house sizes. Annual local heating system operation time and key economic indicators are derived for each case across 3 European countries. A new approach is precise investigation of 10-year outdoor temperatures and apply it to heat pump (HP) modeling, which enabled a distinction between so-called warm and cold years. The results underscore substantial variations in net present value (NPV) between warm and cold years, illustrating the critical influence of precise climate data on the performance of HPs. The study revealed that for a 160 m2 house in Poland, annual electricity consumption by HPs ranged from 3736 kWh during warm years to 12,908 kWh during cold years, showing a significant variation in performance based on climate conditions. The comprehensive tool allows for precise adjustments of heating systems to actual local climate conditions, improving both economic and environmental outcomes. This comparative assessment aids in the optimal selection of HPs, ensuring energy efficiency and sustainability in residential heating systems. Building on studies from various climatic regions, this work addresses the knowledge gap in performance and explores the feasibility of HP in a changing climate using precise modeling techniques.

Research on the framework and meteorological parameter optimization method of dynamic heating load prediction model for heat-exchange stations

Heat-exchange station is the key mid-link between heat source and heat users in district heating system, playing a role in distributing heat and regulating supply and demand. Accurate load prediction at the level of heat-exchange stations and then regulating the heat supply is the important step to optimize district heating system. Based on real and limited data, the framework of heat-exchange station load prediction method is established in this study, which includes 5 procedures ‘data preprocessing method, input variable selection, solar radiation substitution, prediction model establishment and model transplantation application’. The sliding box plot method was proposed for data preprocessing, and the effects of data preprocessing under the widths of 24 h, 48 h, 72 h, 96 h and 120 h were compared, with 48 h as the optimal sliding window width. Support Vector Regression (SVR) algorithm was used to establish a heating load prediction model for heat-exchange station in residential buildings. And parameter substitution was made for solar radiation data that cannot be obtained in weather forecasts. High accuracy was obtained with a MAPE of 5.80 % and RMSE of 0.18 GJ. The above model was transplanted and applied in three other heat-exchange stations of different building types. The MAPEs were 5.51 %, 7.79 % and 6.54 %, with corresponding RMSEs of 0.017 GJ, 0.04 GJ and 0.04 GJ, respectively, which all achieved good prediction results. The research results provide certain technical support for the operation and regulation of district heating systems.

Heat load forecasting model considering two dimensional changes of time series

The regulation strategy of a district heating system is adjusted based on accurate heat load prediction, which not only effectively reduces energy consumption but also improves system efficiency and user comfort. In order to improve the accuracy of heat load forecasting, a heat load forecasting model considering the two-dimensional change of time series is introduced in this paper. Firstly, the original heat load data is denoised by SVMD decomposition, and several stationary and regular modal components are obtained. Then, three strategies were used to enhance the BWO algorithm, and the IBWO-TimesNet prediction model was established to extract the hidden information of time series data from a two-dimensional perspective. Finally, the prediction performance of the model is evaluated in detail through case analysis. The results show that MAE, RMSE and R2 of SVMD-IBWO-TimesNet model are 0.647, 1.190 and 99.1%, respectively. Compared with other mainstream prediction models, this model has higher prediction accuracy. In addition, even if the training samples are reduced, the SVMD-IBWO-TimesNet model can still effectively predict the heat load and has strong generalization ability. Therefore, the performance of the model is verified, which provides a reference for the accurate control of heat load. Practical application Heat load forecasting is a vital task particularly in relation to its impact on the management of building energy efficiency. The contribution of this paper is to provide a heat load forecasting model based on advanced algorithms and data analysis. This insight derived from advanced modelling will assist professionals in the pursuit of more accurate prediction of the heat needs of buildings, thereby optimizing the design and operation of heating systems. The practical application of this technology could save energy costs, reduce carbon emissions, and improve the comfort and sustainability of buildings.

MGMI: A novel deep learning model based on short-term thermal load prediction

Accurate heat load prediction is the key to stable operation and control of district heating system. However, current heat load forecasting methods tend to treat individual buildings as isolated entities, ignoring the temporal and spatial correlation between buildings. In this paper, a heat load forecasting model is proposed which fully considers spatiotemporal information. Firstly, the spatial and temporal relationship between buildings is analyzed by statistical method. Secondly, synchronous wavelet transform (SWT) is used to denoise the heat load data to reduce the difficulty of prediction. Then, a hybrid model of multi-modal graph attention network (MG) and multi-scale Informer (MI) is constructed to capture spatiotemporal information in the data. Finally, an example of DHS in a campus in Liaoyang is analyzed. The results showed that compared with LSTM, CNN-Informer, GCN-LSTM and GAT-Informer, the MAE of MGMI on 168 h test set was reduced by 71.4%, 61.5%, 58% and 41.6%, respectively. And has the highest computational efficiency. The validity of the model is verified, which provides an important basis for the operation control of the thermal system.

A simple load model based on hybrid mechanism and data-driven approach for district heating in building complex

Accurate prediction of heating loads in district heating systems is essential for the implementation of demand-driven heating. This work presents a novel heating load prediction model that is particularly suitable for complex multi-user buildings. The input characteristics of the model are established through the heat transfer mechanism, considering factors such as the cumulative impact of outdoor temperature and user demand (indoor temperature). The specific form of the heating load function is determined using the MLR-PSO (Multiple Linear Regression-Particle Swarm Optimization) method. Only the indoor and outdoor temperatures need to be provided for the model to calculate future heating loads. Practical engineering tests demonstrated that the model achieved normalized mean bias errors of daily loads between 4.98 % and 5.54 % across different heating seasons, with a minimum annual relative deviation of 0.75 % for annual loads. Additionally, the model helps guide the operation of heating systems. For example, during the 2021–2022 heating season, setting the target indoor temperature at 18 °C reduced weekly energy consumption by 15.3 % compared to the previous season. This approach may be employed to construct a simple load model for existing heating systems to accurately predict both short-term and long-term loads, providing valuable insights into the management and control of heating systems.

A novel improved hybrid neural network for predicting heating load in airport building

In order to guarantee the efficient and energy-saving operation and control of airport heating systems, accurate heating load prediction is extremely critical. In view of the relatively little research on heating load prediction of airport buildings, besides, out of these, the fact that the actual characteristics of the airport itself and its production operations should be considered, resulting in inferior performance. Framed in this goal, Initially, the heating area is partitioned. Subsequently, a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm synthesizes it with fuzzy entropy (FE) to decompose the heating load, and the maximum information coefficient integrated with the distance correlation coefficient is utilized for the feature selection. After that, a multi-strategy improved artificial bee colony algorithm (MIABC) algorithm is used to optimize the radial basis function (RBF)neural network and the gated recurrent unit (GRU) neural network, respectively, and the two are combined to construct the hybrid prediction model of the heating load. Finally, actual heating load data is used to verify the prediction performance of the proposed model. Besides, the results show that the root mean square error (RMSE), mean absolute percentage error (MAPE), range of relative error (RRE), and mean bias error (MBE) of the proposed model are 0.465, 1.08 %, 11.42 % and 0.082, respectively, the coefficient of determination (R2) is 0.997, and the prediction accuracy reaches 98.92 %. Additionally, it has more robustness and generalization power, effectively overcoming the heating load's uncertainties and laying a foundation for controlling, monitoring, and managing the buildings' operation.

Indoor Air Quality Assessments in 10 Long-Term Care Facilities during the COVID-19 Pandemic, California, 2021–2023

ObjectivesThis study aimed to assess indoor air quality (IAQ) in long-term care facilities (LTCFs) in California during the COVID-19 pandemic and evaluate their implementation of IAQ best practices described by public health authorities to control respiratory pathogen transmission via inhalation. DesignThis observational study conducted IAQ assessments in a convenience sample of LTCFs to gather qualitative data on the implementation of IAQ best practices. The design included 5 pilot visits to develop a standardized method of data collection and then systematic data collection at 10 facilities. Setting and ParticipantsThe study focused on 10 LTCFs across California, chosen from facilities that responded to flyers advertising free IAQ assessments. Some of the facilities had previously experienced COVID-19 outbreaks affecting residents and staff. MethodsState health department industrial hygienists performed site visits to collect data on each facility's heating, ventilation, and air-conditioning (HVAC) system operation, outdoor air introduction, recirculated air filtration, use of portable air cleaners, and directional airflow in isolation areas to evaluate implementation of IAQ best practices in each of these areas. Qualitative data were obtained through visual inspections and interviews with maintenance personnel. ResultsFindings indicated suboptimal implementation of IAQ best practices across the assessed facilities: no facility operated HVAC systems continuously, 40% had all outdoor air dampers open, 20% used MERV-13 or higher rated filters, 20% used portable air cleaners, and 20% performed directional airflow assessment and management for isolating COVID-19 cases. Conclusions and ImplicationsMost LTCFs assessed were not adhering to IAQ best practices, highlighting a significant opportunity for improvement. IAQ best practices described in this study are achievable with existing systems and are critical for reducing virus transmission through the air in LTCFs. The findings underscore the need for more systematic assessments and improvements in IAQ within LTCFs to protect staff and residents.

Role of power-to-heat and thermal energy storage in decarbonization of district heating

The sector integration of the heat and electricity sectors promotes the flexibility of the energy system. This, together with the already almost carbon dioxide-free electricity supply in Finland, facilitates the environmental transition to a carbon-neutral heating system. In this study, pathways to decarbonize the district heating system in Åland (an autonomous region of Finland) are explored. Especially, the roles of different power-to-heat technologies, e.g., heat pumps and direct electric heating, and thermal energy storage are investigated in the decarbonization of the district heating system. The focus is on studying the impact of varying prices in electricity markets on the operation of climate-neutral district heating systems. For this, three scenarios were modeled over the five years of 2018–2022 with varying demand and electricity market prices by using the modeling software PLEXOS. The study showed that electricity prices, but also reserve market prices, have a very significant impact on the operation cost and profit of a district heating system. Overall, electrification has the strong potential to reduce emissions cost-effectively in a district heating system, but it also makes the system vulnerable to electricity price volatility. It can be concluded that thermal energy storage and reserve market participation are crucial for protecting against cost increases and reducing investment risk.

Model-predictive space heating control for energy flexibility – a case study using a long short-term memory neural network surrogate model and a genetic optimization algorithm

This paper presents a case study where a model predictive control (MPC) logic is developed for energy flexible operation of a space heating system in an educational building. A Long Short-Term Memory Neural Network (LSTM) surrogate model is trained on the output of an EnergyPlus building simulation model. This LSTM model is used within an MPC framework where a genetic algorithm is used to optimize setpoint sequences. The EnergyPlus model is used to validate the performance of the control logic. The MPC approach leads to a substantial reduction in energy consumption (7%) and energy costs (13%) with improved comfort performance. Additional energy costs savings are possible (7–16%) if a sacrifice in indoor thermal comfort is accepted. The presented method is useful for developing MPC systems in the design stages where measured data is typically not available. Additionally, this study illustrates that LSTM models are promising for MPC for buildings.

Research on Intelligent Heating for Urban Systems Based on Digital Twin

Abstract This article focuses on the intelligent heating platform driven by digital twins, analyzing the overall framework of the system according to the sensor layer, application layer, and network layer, and building an information service platform for intelligent heating networks. The data of the entire heating system, including heat sources, primary networks, heating stations, secondary networks, and heat users, is remotely collected, analyzed, and diagnosed. Subsequently, statistical analysis is conducted on the energy consumption of each heat source and heating station, achieving data sharing and data mining among various business systems. This article conducts research on several key technologies for optimizing decision-making methods of heating system operation scheduling based on simulation models and develops software systems to support the intelligent upgrading of heating systems. The results show that intelligent heating system based on digital twins can better meet the balance between supply and demand in urban heating systems, and optimize the overall operating costs and environmental benefits of the system under multiple constraints.

Sparse dynamic graph learning for district heat load forecasting

Accurate heat load forecasting is crucial for the efficient operation and management of district heating systems. This study introduces a novel Sparse Dynamic Graph Neural Network (SDGNN) framework designed to address the complexities of forecasting heat load in district heating networks. The proposed model represents the district heating network as a dynamic graph, with nodes corresponding to consumers or heat sources and edges denoting temporal dependencies. The SDGNN framework comprises three key components: (1) a sparse graph learning module that identifies the most relevant nodes and edges, (2) a spatio-temporal memory enhancement module that captures both short-term and long-term dependencies, and (3) a temporal fusion module that integrates node representations into a comprehensive global forecast. Evaluated on a real-world district heating dataset from Denmark, the SDGNN model demonstrates superior accuracy and efficiency compared to existing methods. The results indicate that the SDGNN framework effectively captures intricate spatio-temporal patterns in historical heat load data, achieving up to 5.7% improvement in RMSE, 7.4% in MAE, and 5.7% in CVRMSE over baseline models. Additionally, incorporating meteorological factors into the model further enhances its predictive performance. These findings suggest that the SDGNN framework is a robust and scalable solution for district heat load forecasting, with potential applications in other domains involving spatio-temporal graph data.

Smart Spam Detection and Correction for Temperature in Heater

The efficient operation of heating systems relies heavily on accurate temperature monitoring. However, such systems are vulnerable to data corruption, which can lead to erroneous temperature readings and potentially hazardous conditions. We propose a novel approach to address this challenge by employing machine learning techniques for spam detection and correction in heater temperature data for the detection phase. We explore various machine learning algorithms including spam detection and classification models, to identify spam temperature readings. These models are trained on the preprocessed dataset and evaluated using appropriate metrics to assess their performance.

Integrating Low Temperature Waste Heat in District Heating Systems. Legal Framework and Pricing Mechanisms

ABSTRACT:Decarbonisation the heating sector is a key challenge for the European Union to achieve its ambitious goals of becoming the first climate - neutral continent in 2050. Decarbonising the heating sector is about reducing fossil fuel consumption and finding new scenarios based on renewables and restructuring the operation of district heating system. Recovering and integration waste heat into the district heating system has an enormous potential to meet the heating needs of households through non – combustion technologies while reducing carbon emissions. The heat from urban sources of waste heat is advantageous because the heat sources are, close to district heating networks and close to areas with high heat demand. However, there is still no legal or regulatory framework for the use of waste heat and no incentives for its use in district heating in the Member States of EU.This paper has two main objectives: firstly, to consider different pricing and cost determination scenarios when the waste heat is integrated into the district heating system. The heat tariff calculation model is based on the approved Latvian heat tariff calculation methodology. Secondly – to consider a mathematical model for the pricing of waste heat. The waste heat integration strategies are tested on the Case study of district heating system in Salaspils, Latvia. Simplified model of a waste heat recovery system that recovers heat energy from a wastewater treatment plant through heat pump integration is developed.