1,720,971 research outputs found
Data-driven fault detection and diagnosis: research and applications for HVAC systems in buildings
Full text linkA data analytics-based energy information system (EIS) tool to perform meter-level anomaly detection and diagnosis in buildings
Full text linkRecently, the spread of smart metering infrastructures has enabled the easier collection of building-related data. It has been proven that a proper analysis of such data can bring significant benefits for the characterization of building performance and spotting valuable saving opportunities. More and more researchers worldwide are focused on the development of more robust frameworks of analysis capable of extracting from meter-level data useful information to enhance the process of energy management in buildings, for instance, by detecting inefficiencies or anomalous energy behavior during operation. This paper proposes an innovative anomaly detection and diagnosis (ADD) methodology to automatically detect at whole-building meter level anomalous energy consumption and then perform a diagnosis on the sub-loads responsible for anomalous patterns. The process consists of multiple steps combining data analytics techniques. A set of evolutionary classification trees is developed to discover frequent and infrequent aggregated energy patterns, properly transformed through an adaptive symbolic aggregate approximation (aSAX) process. Then a post-mining analysis based on association rule mining (ARM) is performed to discover the main sub-loads which mostly affect the anomaly detected at the whole-building level. The methodology is developed and tested on monitored data of a medium voltage/low voltage (MV/LV) transformation cabin of a university campus
Recognition and classification of typical load profiles in buildings with non-intrusive learning approach
Full text linkThe recent increasing spread of Advanced Metering Infrastructure (AMI) has enabled the collection of a huge amount of building related-data which can be exploited by both energy suppliers and users to gain insight on energy consumption patterns. In this context, data analytics-based methodologies can play a key role for performing advanced characterization, benchmarking and classification of buildings according to their typical energy use in the time domain. Traditionally, energy customers are classified according to their building end-use category. However, buildings belonging to the same category can exhibit very different energy patterns making ineffective this kind of a-priori categorization. For this reason, load profiling frameworks have been developed in the last decade to identify homogenous groups of buildings with similar daily energy profiles. The present study proposes a non-intrusive customer classification process, which does not use as predictive attributes in-field load monitoring data for the classification of unknown customers, but rather monthly energy bills and additional information on customers’ habits collected by means of a phone survey. The proposed classification process is developed by analysing hourly energy consumption data of 114 electrical customers of an Italian Energy Provider. The representative daily load profiles are grouped using the “Follow the Leader” clustering algorithm and a globally optimal decision tree is employed to build a supervised classification model. The model, compared to a baseline recursive partitioning tree, leads to an increase of accuracy of about 6%. Eventually, the procedure exploits energy bill data also for estimating the magnitude of typical load profiles
A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings
Full text linkIn this paper, a tool for the detection and diagnosis of anomalous electrical daily energy patterns relative to a transformer substation of a university campus was developed and tested. Through an innovative pattern recognition analysis consisting in a multi-step clustering process, six clusters of anomalous daily load profiles were identified and isolated in two-year historical data of total electrical energy consumption. The infrequent electrical load profiles were found to be strongly affected, in terms of both shape and magnitude, by the energy consumption behaviour related to the heating/cooling mechanical room. Then, a fault-free predictive model, which uses artificial neural network (ANN) in combination with a Regression Tree, was developed to detect anomalous trends of the electrical energy consumption. The model was able to detect the 93.7% of the anomalous profiles and only the 5% of fault-free days were wrongly predicted as anomalous. Eventually, a diagnosis phase was conceived and validated with a testing data set. A number of daily abnormal load profiles were detected and compared with the centroids of the anomalous clusters identified in the pattern-recognition stage. The work led to the development of a flexible intelligent tool useful for operating a continuous commissioning of the campus facilities
Enhancing operational performance of AHUs through an advanced fault detection and diagnosis process based on temporal association and decision rules
Full text linkThe pervasive monitoring of HVAC systems through Building Energy Management Systems (BEMSs) is enabling the full exploitation of data-driven based methodologies for performing advanced energy management strategies. In this context, the implementation of Automated Fault Detection and Diagnosis (AFDD) based on collected operational data of Air Handling Units (AHUs) proved to be particularly effective to prevent anomalous running modes which can lead to significant energy waste over time and discomfort conditions in the built environment. The present work proposes a novel methodology for performing AFDD, based on both unsupervised and supervised data-driven methods tailored according to the operation of an AHU during transient and non-transient periods. The whole process is developed and tested on a sample of real data gathered from monitoring campaigns on two identical AHUs in the framework of the Research Project ASHRAE RP-1312. During the start-up period of operation, the methodology exploits Temporal Association Rules Mining (TARM) algorithm for an early detection of faults, while during non-transient period a number of classification models are developed for the identification of the deviation from the normal operation. The proposed methodology, conceived for quasi real-time implementation, proved to be capable of robustly and promptly identifying the presence of typical faults in AHUs
Online implementation of a soft actor-critic agent to enhance indoor temperature control and energy efficiency in buildings
Full text linkRecently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively
Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings
Full text linkIn this work, Deep Reinforcement Learning (DRL) is implemented to control the supply water temperature setpoint to terminal units of a heating system. The experiment was carried out for an office building in an integrated simulation environment. A sensitivity analysis is carried out on relevant hyperparameters to identify their optimal configuration. Moreover, two sets of input variables were considered for assessing their impact on the adaptability capabilities of the DRL controller. In this context a static and dynamic deployment of the DRL controller is performed. The trained control agent is tested for four different scenarios to determine its adaptability to the variation of forcing variables such as weather conditions, occupant presence patterns and different indoor temperature setpoint requirements. The performance of the agent is evaluated against a reference controller that implements a combination of rule-based and climatic-based logics. As a result, when the set of variables are adequately selected a heating energy saving ranging between 5 and 12% is obtained with an enhanced indoor temperature control with both static and dynamic deployment. Eventually the study proves that if the set of input variables are not carefully selected a dynamic deployment is strictly required for obtaining good performance
The impact of stakeholder preferences in multicriteria evaluation for the retrofitting of office buildings in Italy
Full text linkBuildings are responsible for about 26% of the total final energy consumption in Italy. Therefore, building retrofitting represents an opportunity to achieve economic and environmental benefits. However, a challenging task is the application of robust methodologies for evaluating cost-optimal retrofit measures. The paper evaluates, in terms of multiple criteria-based approach, several retrofitting alternatives selected for a typical office building in Italy. The alternatives are evaluated considering economic, environmental, and technical requirements and are compared by means of a Stochastic Multicriteria Acceptability Analysis (SMAA) method, able to consider uncertainties in the criteria evaluation. Three different stakeholder preferences are analyzed and compared with the aim to point out the importance of preference information in multicriteria analysis. The results highlight that, when the preference is the investment cost, for the case study analyzed the most suitable solution is represented by a gas boiler and electricity withdrawn from the market. On the other hand, when the operational cost has the same or more importance than the investment cost, the best solution is represented by a micro-CHP coupled with PV plant. Lastly, the analysis highlights that the main driver of a building retrofit is of economic nature and that, depending on the actors involved, a precise study of preference information could influence the outcome of the analysis
Bridging the gap between complexity and interpretability of a data analytics-based process for benchmarking energy performance of buildings
Full text linkArtificial intelligence (AI) is fast becoming a general purpose technology with outstanding impacts in industries worldwide, thus supporting the Industry 4.0 revolution. In particular, the energy sector is one of those that has taken more advantages from the implementation of AI approaches, especially Machine Learning models, for several applications, including energy performance benchmarking of buildings. However, the black-box approach could lead to a lack of result interpretability thus preventing the effective application of AI in some real-world scenarios. For this reason, eXplainable Artificial Intelligence (XAI) tools can be effectively embedded within an AI-based Energy Analytics methodology in order to enhance the explainability of the model results. In this paper, we propose an explainable AI-based benchmarking framework for estimating the membership to specific energy performance classes of a large set of Energy Performance Certificates (EPCs) of flats. The classification is obtained by leveraging different black-box classifiers characterized by high accuracy, yet their inference mechanism is not human-readable. Therefore, a generalizable XAI methodology, based on the combination of a local explainer together with a clustering algorithm, is employed to explain the model results and causal effects between the predictors and target variable to better understand the model behaviour, and the motivations behind correct and wrong performed classifications. The paper provides a general methodological approach capable to exploit a limited number of instances to extract, explain and interpret inference mechanisms learnt by the model that are useful for the end-user. The framework was tested on about 100,000 EPCs of flats located in Italy
Towards a self-tuned data analytics-based process for an automatic context-aware detection and diagnosis of anomalies in building energy consumption timeseries
Full text linkRecently, the spread of IoT technologies has led to an unprecedented acquisition of energy-related data providing accessible knowledge on the actual performance of buildings during their operation. A proper analysis of such data supports energy and facility managers in spotting valuable energy saving opportunities. In this context, anomaly detection and diagnosis (ADD) tools allow a prompt and automatic recognition of abnormal and non-optimal energy performance patterns enabling a better decision-making to reduce energy wastes and system inefficiencies. To this aim, this paper introduces a novel meter-level ADD process capable to identify energy consumption anomalies at meter-level and perform diagnosis by exploiting information at sub-load level. The process leverages supervised and unsupervised analytics techniques coupled with the distance-based contextual matrix profile (CMP) algorithm to discover infrequent subsequences in energy consumption timeseries considering specific boundary conditions. The proposed process has self-tuning capabilities and can rank anomalies at both meter and sub-load level by means of robust severity score. The methodology is tested on one-year energy consumption timeseries of a medium/low voltage transformation cabin of the university campus of Politecnico di Torino leading to the detection of 55 anomalous subsequences that are diagnosed by analysing a group of 8 different sub-loads
- …
