Search

This paper provides a method for predicting the energy efficiency of buildings using artificial intelligence tools. The scopes is twofold: prediction of the levels of the heating load and cooling load of buildings. A feature of this research is the performance of intellectual analysis in conditions of a limited amount of data when solving the stated tasks. An improved method of augmentation and prediction (input-doubling method) is proposed by processing data within each cluster of the studied dataset. The selection of the latter occurs due to the use of the fast and easy-to-implement k-means method. Next, a prediction is made using the input-doubling method within each separate cluster. The simulation of the method was performed on a real-world dataset of 768 observations. The proposed approach was found to have a high prediction accuracy in the absence of overfitting and high generalization properties of the improved method. Comparison with existing methods showed an increase in accuracy by 40-46% (MSE) compared to SVR with rbf kernel, which is the basis for the improved method, and by 5-12% (MSE) compared to the closest existing hierarchical predictor. [ABSTRACT FROM AUTHOR]

• A two-step framework for grey-box modeling of building thermal dynamics. • Parameter identification under fluctuating data from direct expansion system. • Determined optimal complexity and data frequency in case study. • New evaluation metric that considers accumulated energy value for load prediction. Thermal dynamics model plays a crucial role of advanced control in the intelligent building. Grey box method is widely used in the modeling of building thermal dynamics based on the operation data of air-conditioner. The performance of direct-expansion (DX) system fluctuated severely during its operation, which leads to the difficulties in identification and evaluation of the building thermal model. In this paper, a two-step identification framework for second-order thermal resistance-capacity network of building based on DX system data is proposed. A case study is conducted on an office building equipped with variable refrigerant flow system in Foshan, China. The results show that the proposed framework can identify the parameters rationally. The model achieves high accuracy for both indoor temperature (Mean absolute errors of 0.74°C) and cooling load prediction (Mean absolute errors of 4453.86W) in a short time interval of 10 minutes. Additionally, the best complexity of the grey-box model for case building and the data acquisition interval is determined. Finally, an improved set of evaluation metrics for thermal load evaluation is proposed and discussed. [ABSTRACT FROM AUTHOR]

In this paper, numerical simulations of Diffusion Absorption Refrigeration – DAR cycle were conducted in order to study the performance of two configurations in steady state mode and use ammonia, water, hydrogen as working fluids. The two configurations were numerically simulated using models developed with the commercial flow sheet Aspen HYSYS V10 software. The first configuration where the main simple DAR cycle components were simulated and validated the experimental results. The second configuration where the modified DAR cycle was simulated which has an auxiliary heat exchanger added to the main simple DAR cycle as a modification. It was found that for the same input assumptions and heat applied, the modified DAR cycle shows higher cooling load. Therefore, higher COP than the simple DAR cycle. The optimal operation of the modified cycle is 36 W applied to the generator to achieve a COP of 0.235 instead of 0.209 for simple DAR cycle. The Simulation results show that by using the modified cycle, the COP improves by 12.4%. [ABSTRACT FROM AUTHOR]

• Performance of the ejector refrigerator was studied under different ejector profiles. • Significant performance improvement was achieved when using the CRMC–ejector. • The T chill produced by CRMC–ejector was much lower than CONV–ejector. • The CRMC–ejector produced better performance under various working conditions. • The system COP can be increased by 27–63% via the CRMC–ejector. This paper proposes the performance improvement of the ejector refrigerator based water chiller (ejector-based chiller) by means of using different mixing chamber profiles. Two different ejector mixing chamber profiles are constructed which are based on the conventional method (CONV–ejector) and the constant rate of momentum change method (CRMC–ejector). With the different design methods, the ejectors have different flow areas along the ejector's axis; however, they have identical ejector throat diameters of 9 mm. Both ejectors are equipped with two primary nozzles, and hence, they have the same ejector area ratio of 6.3 and 7.9, respectively. The refrigerator is powered by hot water at a temperature of 94–98 °C while the condenser is cooled by cooling water at 29–31 °C. The chilled water temperature (T chill) under various cooling loads and COP is assessed. It is found that the CRMC–ejector produces a much lower chilled water temperature than the CONV–ejector at identical cooling load. The system COP can be increased by 27–63% via the CRMC–ejector. With the change in T hot , both ejectors produce identical T chill ; however, the CRMC–ejector still produces much lower T chill at an identical cooling load. A larger primary nozzle throat yields a higher T chill. [ABSTRACT FROM AUTHOR]

• Developed an improved attention-based approach for robust cooling load prediction. • Generated hourly cooling loads under diverse occupancy schedules. • Highlighted the impact of temporal characteristics on prediction performances. • Introduced a time representation learning and attention mechanism to improve accuracy. • Combining XGB to enhance prediction accuracy, robustness, and transparency. Space cooling in buildings is responsible for massive energy consumption and carbon emissions. Accurate cooling load prediction can facilitate the implementation of energy-efficiency cooling control strategies in practice. In this paper, an improved attention-based deep learning approach is proposed for robust ultra-short-term cooling load prediction. First, a novel time representation learning is introduced to extract the periodicity and non-periodicity of cooling loads efficiently. Then, long short-term memory with an attention mechanism extracts properly the time steps by identifying the relevant hidden states and learns high-level temporal dependency. The approach additionally incorporates extreme gradient boosting through the error reciprocal method, enhancing the elimination of prediction errors and improving robustness. The study takes Guangzhou as an example and generates cooling loads using diverse occupancy schedules of five building types based on the Chinese National Standard and Typical Meteorological Year data. The approach is evaluated on datasets comprising the cooling loads, meteorological data, and contextual information. Through results analysis, the approach outperforms other models in terms of prediction accuracy and robustness across all building types. Additionally, model interpretation is provided regarding feature importance and attention matrixes, which enhances the understanding and transparency of the final prediction from the proposed approach. [ABSTRACT FROM AUTHOR]

• Modeling a multi-energy retailer in the framework of multi-carrier energy systems. • Developing a multi-energy retailer based on gas/cooling/heating/power carriers. • Presenting an IGDT method to cope with uncertainties in the optimization model. • Integrating flexible options, e.g. hybrid energy storage in the optimization model. • Proposing integrated DR to control multiple energy demands simultaneously. Multi-energy systems (MESs) were introduced to enhance the flexibility and efficiency of conventional energy distribution systems. In this new trend, it is possible to supply different energy carriers simultaneously by the multi-energy retailer (MER), under which, without the need to transfer all of them to different locations, the loads are fed centrally, and the customers can purchase all the carriers they need from the desired MER. Motivated by these descriptions, this paper focuses on the optimal scheduling of MER in the integrated energy system, including natural gas, electricity, cooling, and heating, under the information gap decision theory (IGDT) framework. The MER's goal is to maximize profits by considering the uncertainty of the day-ahead power market. The proposed IGDT approach without a probabilistic distribution function analyzes the risk-aversion strategy associated with electricity price uncertainty. In this paper, integrated demand response (IDR) for natural gas, electrical, heating, and cooling loads are developed simultaneously as a flexible demand-side management resource. The proposed model contains multiple technologies owned by MER, including hybrid energy storage technology, combined heat and power, chiller, boiler units, and renewable resources. Numerical results from different cases illustrate the effectiveness of IDR installation in terms of profitability. Besides, the MER can serve multiple demands more efficiently. Under the IGDT approach, the purchasing power cost is reduced up to 24.23%. [ABSTRACT FROM AUTHOR]

• New comprehensive framework for a CCHP-based MG operation. • New CCP approach for guaranteeing confidence level of the whole system. • Proposing a comparative structure for participating in power and heat markets. • Utilizing multi-carrier storage, hybrid chiller, besides new mathematical for CHP. Microgrids (MGs) have a special role in developing several consumers' energy infrastructure and supply in more economical, safer, and sustainable ways. The interaction and mutual relationship between each energy carrier on the reliable performance of other carriers and the high growth of tri-generation technologies in the MG face the optimal performance of such networks with many challenges. Combined cooling, heating, and power (CCHP)-based MGs are a new generation of MGs that simultaneously provide electrical, thermal, and cooling loads. However, the interaction between these carriers is very influential in CCHP-based MG's operation, which is rarely analyzed. Hence, this paper focuses on the operation of CCHP-based MG coupled with hybrid chiller, multi-energy storage, solar and wind power, etc., under the chance-constrained programming (CCP) approach by considering the mutual relationship between carriers. While modeling consumption and wind and solar energies fluctuations, the proposed approach analyzes the violation of the balance constraint for each carrier and subject it to guarantee the corresponding confidence level. Therefore, the degree of dependence of the system on each carrier and the mutual relationship between carriers are analyzed in this work. This paper also presents a new incentive framework for participating in the electricity and heating markets for the system. The proposed model is implemented on the test system, and the results are discussed for different cases for several confidence levels. The results illustrate the importance of the electricity carrier confidence level on the safe performance of the whole system compared to other carriers. Only by increasing the operation cost of the electricity sector by 4.3%, the system's reliable performance is guaranteed with a probability of 98%. [ABSTRACT FROM AUTHOR]

Global warming and the urban heat island effect have led to the deterioration of the outdoor thermal environment and the rise of building cooling demand, calling for urban design with high environmental quality. However, little has been changed in the practice of urban street design. This paper bridges this gap by developing a framework of parametric simulation for design guidance of urban streets with an advanced urban canopy model that can simulate the interactive indoor-outdoor environment. Case studies are conducted at the neighborhood scale for six cities to improve outdoor thermal comfort and building energy efficiency in summer. The influence of street and building design parameters has been investigated based on 31104 simulations. Results reveal the conflict between optimizing outdoor thermal comfort and optimizing building energy efficiency. In the majority of the investigated cities, window-to-wall ratio, window type, and street orientation are the most influential parameters. Strategies by adjusting these parameters can significantly improve outdoor thermal comfort, as quantified by thermal stress hours, at a cost of increasing the building cooling load. Planting bigger and denser roadside trees always moderately reduces the thermal stress hours and building cooling load. These results demonstrate the potential of this framework to identify the design trade-offs between thermal comfort and building energy efficiency. The framework can be extended to various cities to help designers and policymakers at the early design stage. • A framework to explore early design guidance for urban streets is developed. • A total of 31104 design scenarios are performed for six cities in southern China. • Window-to-wall ratio, window type, and street orientation are most influential factors. • Pareto optimal solutions for outdoor thermal comfort and building energy are revealed. [ABSTRACT FROM AUTHOR]

For the better operation of air-conditioning systems and the improvement of office building thermal environment, internal heat loads resulting from occupants, equipment, and lightings need to be accurately quantified because they are main components of space cooling loads. However, existing methods are hard to describe the complicated variation characteristics of internal cooling loads and time lag effect of conversion processes between electric energy and internal cooling loads, leading to limited application and unstable accuracy. To tackle this problem, in this study, transfer function models for instantaneous internal cooling loads were firstly established. Second, an experiment was conducted based on a chamber with good insulation. Third, experimental data and radiant time factors were employed in model discretization, parameter identification, and order decrease steps to acquire unknown parameters and develop models as second-order and third-order discrete transfer functions. Fourth, a simulation was conducted to validate the models, and a mean absolute percentage error of 8.08% was attained. Finally, a comparison between proposed and previously developed methods was carried out to evaluate model performance. The proposed models achieved a maximum internal cooling loads reduction of 75.57%, and the maximum time lag resulting from the heat storage characteristics of indoor thermal masses was approximately 30 min. With two easily accessible input parameters, the proposed models exhibited promising applicability and feasibility during the real-time operation of buildings. This paper provides a theoretical basis for accurately obtaining instantaneous internal cooling loads and thus is meaningful in improving building thermal environment and enhancing comfort levels. • Transfer function models for acquiring instantaneous internal cooling load were developed. • With two accessible input parameters, proposed models were applicable to the operation of office buildings. • Compared with previous methods, a maximum decrease in errors of 75.57% was obtained after adopting the proposed models. • This study facilitated the description of time lag effect of conversion processes between electric energy and internal cooling loads. [ABSTRACT FROM AUTHOR]

• Technical-economic analysis of the combined cooling, heating, power, fresh water and hydrogen generation system (CCHPWH) are presented. • Optimization of the studied system was used by the genetic algorithm to obtain the minimum total annual cost (TAC). • CCHPWH system by the prime mover of gas engine has 10% lesser TAC than the system by the prime mover of gas turbine. • Exergy efficiency of the cogeneration system in the optimal state for the prime mover of the gas turbine and the gas engine was 31.21 and 45.58%. Multi-generation plant is a decentralized, energy-efficient method of different type of energy production. Such a system can deliver multiple benefits and advantages compared to conventional energy production such as improvement in the efficiency, emission, cost and reliability. Technical-economic analysis of the combined cooling, heating, power, freshwater and hydrogen generation system (CCHPWH) are presented in this paper. Selecting the nominal power of prime movers, their numbers, the cooling capacity of absorption and electrical chillers, the heating capacity of auxiliary boiler, electric cooling ratio (the ratio of electrical chiller capacity to the cooling load demand), motive steam pressure, number of effects, motive steam flow rate, feed flow rate and 24 partial loads for the prime mover during in the year are considered as 35 design parameters. The optimization of the studied system was used by the genetic algorithm to obtain the minimum total annual cost (TAC) as an objective function. The total annual cost includes economic, energy and environmental parameters. It should be noted that selling/buying electricity to/from the grid is allowable in this study. The optimum results showed 24.8% reduction in the total annual cost of the CCHPWH system using a gas engine as prime mover as compared with a gas turbine. In addition, the exergy efficiency of the cogeneration system in the optimal state for the prime mover of the gas turbine and the gas engine was obtained 31.21% and 45.58%, respectively. Finally, the optimal results in different cases were compared and results were discussed. [Display omitted] [ABSTRACT FROM AUTHOR]

In this paper, the application of smart glazing systems as shading devices is evaluated for US residential buildings. Specifically, static and dynamic overhangs are considered using smart glazing that can change their tint state to reduce the heating and cooling thermal loads for prototypical housing units in high-rise apartment buildings. The tint settings as well as the overhang tilt angles are specified on hourly, daily, and monthly basis depending on the window orientation and the time of the year to minimize the annual energy demand for the housing units. The performance of smart glazed overhang systems is compared to both static and dynamic shading devices made-up of conventional opaque materials. In addition, the impacts of various design and climatic conditions are considered to assess the energy performance of the smart glazed overhangs. The results of the analysis indicate that the annual energy consumption for existing housing units with conventional windows located in Boulder, CO, can be reduced by over 7% for static smart glazed overhangs and by over 22% for dynamic smart glazed overhangs. These savings are even higher with larger windows and wider differentials between optical properties between clear and dark states. The smart glazed overhangs allow the use of low-cost smart glazing as a retrofit measure for existing buildings. Moreover, the smart glazed overhangs allow the specification of large windows for new constructions with limited energy penalties. • The energy performance of smart glazed overhangs is investigated for housing units. • Optimal controls are used to maximize the energy efficiency of the smart shades. • Switching of smart shades can be optimized on hourly, daily, or monthly basis. • Smart shades reduce energy demand up to 22% compared to unshaded clear low-E glazing. [ABSTRACT FROM AUTHOR]

• A NILM method of cooling load is proposed for smart buildings based on random forest. • Total cooling load is disaggregated into four sub-loads for building/HVAC optimization. • Two approaches are used depending on the availability of weather data. • The proposed NILM methods can realize load disaggregation accurately. Accurate load monitoring can provide detailed information for users to improve the energy efficiency of buildings. Non-intrusive load monitoring (NILM) has become popular in smart buildings because of its low cost and reasonable privacy. In this paper, a non-intrusive monitoring method for the cooling load of smart buildings is proposed based on random forest. The total building cooling load is disaggregated into four subloads, and two approaches are used to realize the NILM based on the direct or indirect cooling load using a Fourier transform. The proposed method is implemented in an office building, and results show the method can realize cooling load disaggregation accurately. The root-mean-square errors and mean relative errors of the four subloads between the NILM loads and reference loads are less than 51.9 kW and 19.1%. Among the four subloads, the equipment load can be disaggregated with the highest accuracy. Approach I is recommended because of its higher accuracy. The NILM method is optimized in terms of the estimator number, maximum depth, feature number, minimum samples for a split, minimum sample leaf, and size of training samples. The performance of the optimized NILM models is improved with RMSEs and MREs less than 48.3 kW and 6.4%. [ABSTRACT FROM AUTHOR]