This page has only limited features, please log in for full access.
An effective and accurate building energy consumption prediction model is an important means to effectively use building management systems and improve energy efficiency. To cope with the development and changes in digital data, data-driven models, especially deep learning models, have been applied for the prediction of energy consumption and have achieved good accuracy. However, as a deep learning model that can process high-dimensional data, the model often lacks interpretability, which limits the further application and promotion of the model. This paper proposes three interpretable encoder and decoder models based on long short-term memory (LSTM) and self-attention. Attention based on hidden layer states and feature-based attention improves the interpretability of the deep learning models. A case study of one office building is discussed to demonstrate the proposed method and models. Firstly, the addition in future real weather information yields only a 0.54% improvement in the MAPE. The visualization of the model attention weights improves the interpretability of the model at the hidden state level and feature level. For the hidden state of different time steps, the LSTM network will focus on the hidden state of the last time step because it contains more information. The Transformer model gives almost equal attention weight to each day in the coding sequence. For the interpretable results at the feature level, daily max temperature, mean temperature, min temperature, and dew point temperature are the four most important features. The four characteristics of pressure, wind speed-related features, and holidays have the lowest average weights.
Yuan Gao; Yingjun Ruan. Interpretable deep learning model for building energy consumption prediction based on attention mechanism. Energy and Buildings 2021, 111379 .
AMA StyleYuan Gao, Yingjun Ruan. Interpretable deep learning model for building energy consumption prediction based on attention mechanism. Energy and Buildings. 2021; ():111379.
Chicago/Turabian StyleYuan Gao; Yingjun Ruan. 2021. "Interpretable deep learning model for building energy consumption prediction based on attention mechanism." Energy and Buildings , no. : 111379.
In the existing station network planning of distributed energy systems (DESs), most of them determined the location of energy station in the alternative station site, there was a lack of a mature energy station location optimization method, and the factor load was not considered in the division of energy supply scope. This paper aimed to propose an optimal site approach for distributed energy stations based on Voronoi diagram, in which all possible candidates of energy station locations were considered. The candidate sites could be any point in the whole area. Simultaneously, after analyzing the limitations of the traditional energy supply partition method, we proposed a new energy supply partition optimization method, relative-load-distance. It was found that the annual cost of the whole system was significantly reduced by 1%, although the cost of the network in the optimized supply area was increased, compared with the supply area obtained by the partition method based on the principle of minimum distance. In addition, by adjusting the coefficient K in the relative-load-distance, the effectiveness of the optimization method in DES planning was verified.
Jiazheng Wu; Jiamin Yuan; Yingjun Ruan; Fanyue Qian; Hua Meng. Optimal Planning for Energy Stations and Networks in Distributed Energy Systems Based on Voronoi Diagram and Load Characteristics. Applied Sciences 2021, 11, 7526 .
AMA StyleJiazheng Wu, Jiamin Yuan, Yingjun Ruan, Fanyue Qian, Hua Meng. Optimal Planning for Energy Stations and Networks in Distributed Energy Systems Based on Voronoi Diagram and Load Characteristics. Applied Sciences. 2021; 11 (16):7526.
Chicago/Turabian StyleJiazheng Wu; Jiamin Yuan; Yingjun Ruan; Fanyue Qian; Hua Meng. 2021. "Optimal Planning for Energy Stations and Networks in Distributed Energy Systems Based on Voronoi Diagram and Load Characteristics." Applied Sciences 11, no. 16: 7526.
ZEHs (Zero Energy House) featuring energy-efficient designs and on-site renewable integration are being widely developed. This study introduced Japanese ZEHs with well-insulated thermal envelopes and investigated their detailed operational performances through on-site measurements and simulation models. Measurement data show that ZEHs effectively damped the variation of indoor air temperature compared to conventional houses, presenting great ability to retain inside heat energy, and are expected to potentially deliver energy flexibility as a virtual thermal energy storage medium. We developed a simplified thermal resistance–capacitance model for a house heating system; response behaviors were simulated under various scenarios. Results compared the variations of indoor temperature profiles and revealed the dependence of load flexibility on the building’s overall heat loss performance. We observed that overall heat loss rate played a crucial role in building heat energy storage efficiency; a well-insulated house shortened the heat-up time with less energy input, and extended the delayed period of indoor temperature under intermittent heating supply; a high set-point operative temperature and a low ambient temperature led to lower virtual thermal energy storage efficiency. The preheating strategy was simulated as an effective load-shifting approach in consuming surplus PV generation; approximately 50% of consumed PV generation could be shifted to replace grid import electricity for room heating during the occupied period.
Xiaoyi Zhang; Weijun Gao; Yanxue Li; Zixuan Wang; Yoshiaki Ushifusa; Yingjun Ruan. Operational Performance and Load Flexibility Analysis of Japanese Zero Energy House. International Journal of Environmental Research and Public Health 2021, 18, 6782 .
AMA StyleXiaoyi Zhang, Weijun Gao, Yanxue Li, Zixuan Wang, Yoshiaki Ushifusa, Yingjun Ruan. Operational Performance and Load Flexibility Analysis of Japanese Zero Energy House. International Journal of Environmental Research and Public Health. 2021; 18 (13):6782.
Chicago/Turabian StyleXiaoyi Zhang; Weijun Gao; Yanxue Li; Zixuan Wang; Yoshiaki Ushifusa; Yingjun Ruan. 2021. "Operational Performance and Load Flexibility Analysis of Japanese Zero Energy House." International Journal of Environmental Research and Public Health 18, no. 13: 6782.
This paper proposes a new network topology design method that considers all the road nodes, energy stations and load centers to ensure the distribution of pipes along the road. The traditional graph theory and Prim Minimum Spanning Tree (MST) are used to simplify the map and minimize the length of the pipeline. After analyzing the limitations of the traditional network topology model, Point-to-Point (PTP), we present a new model, Energy Station-to-Load Point (ESLP). The model is optimized by minimum cost, not the shortest path. Finally, Pipe Diameter Grading (PDG) is proposed based on ESLP by solving for the pipe diameter that gives the minimum cost under different load demands in the process of optimization. The network design method is effectively applied in a case, and the results show that the path of the optimized plan is 1.88% longer than that of the pre-optimized plan, but the cost is 2.38% lower. The sensitivity analysis shows that the cost of pipeline construction, project life and electricity price all have an impact on the optimization results, and the cost of pipeline construction is the most significant. The difference between the different classifications of pipelines affects whether PDG is effective or not.
Jiazheng Wu; Hongyun Liu; Yingjun Ruan; Shanshan Wang; Jiamin Yuan; Hui Lu. A Novel Method for Network Design and Optimization of District Energy Systems: Considering Network Topology Planning and Pipe Diameter. Applied Sciences 2021, 11, 1795 .
AMA StyleJiazheng Wu, Hongyun Liu, Yingjun Ruan, Shanshan Wang, Jiamin Yuan, Hui Lu. A Novel Method for Network Design and Optimization of District Energy Systems: Considering Network Topology Planning and Pipe Diameter. Applied Sciences. 2021; 11 (4):1795.
Chicago/Turabian StyleJiazheng Wu; Hongyun Liu; Yingjun Ruan; Shanshan Wang; Jiamin Yuan; Hui Lu. 2021. "A Novel Method for Network Design and Optimization of District Energy Systems: Considering Network Topology Planning and Pipe Diameter." Applied Sciences 11, no. 4: 1795.
Precise prediction of energy consumption in buildings could significantly optimize strategies for operating building equipment and release the energy savings potential of buildings. With advances in computer science and smart meters, data-driven energy forecasting models, particularly deep learning models, are becoming increasingly popular and can achieve good prediction accuracy. However, these models require a multitude of historical data from predicted buildings for training, which are difficult to acquire for newly constructed buildings or buildings with newly established measurement equipment. In order to obtain satisfactory prediction accuracy under such poor information state, this paper proposes two deep learning models, which are a sequence-to-sequence (seq2seq) model and a two dimensional (2D) convolutional neural network (CNN) with an attention layer, and transfer learning framework to improve prediction accuracy for a target building. A case study of three office buildings is discussed to demonstrate the proposed method and models. Compared with the results of a long short-term memory (LSTM) network with poor information state, the seq2seq model improved forecast accuracy for a building with a small quantity of data by 19.69 percentage points in mean absolute percentage error (MAPE), and the 2D CNN model by 20.54 percentage points, on average.
Yuan Gao; Yingjun Ruan; Chengkuan Fang; Shuai Yin. Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data. Energy and Buildings 2020, 223, 110156 .
AMA StyleYuan Gao, Yingjun Ruan, Chengkuan Fang, Shuai Yin. Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data. Energy and Buildings. 2020; 223 ():110156.
Chicago/Turabian StyleYuan Gao; Yingjun Ruan; Chengkuan Fang; Shuai Yin. 2020. "Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data." Energy and Buildings 223, no. : 110156.
Increasing renewable penetration will profoundly affect the grid balance scenario, such as thermal generator flexibility, storage utilization and renewable market value. This paper explores the variabilities and impacts of massive PV integrated into grid with hydro pump balance dispatch, based on real chronological order data of Kyushu. The PV feed-in and storage dispatch conditions are described and compared among seasons, PV integration can greatly shape the net grid load, analysis shows that pump solar energy will increase when its generation excesses around 35.0% ratio of residual load (subtracting nuclear constant output). Hydro pump storage effectively absorbs the excess solar production and maintains the grid flexibility. Further increasing integrated PV capacity will lead necessary output suppression due to limitation of grid flexibility and pump storage ability, the utilization frequency of storage system will be enhanced. When the PV penetration increases from 8.15% to 12.0%, the effective PV utilization per capacity will drop (8.0%) due to the pump cycle loss and output curtailment. The proposed approach and analysis result could extended and provide references for similar utilities with variable renewable energy expansion plan.
Yanxue Li; Weijun Gao; Yingjun Ruan. Quantifying variabilities and impacts of massive photovoltaic integration in public power systems with PHS based on real measured data of Kyushu, Japan. Energy Procedia 2018, 152, 883 -888.
AMA StyleYanxue Li, Weijun Gao, Yingjun Ruan. Quantifying variabilities and impacts of massive photovoltaic integration in public power systems with PHS based on real measured data of Kyushu, Japan. Energy Procedia. 2018; 152 ():883-888.
Chicago/Turabian StyleYanxue Li; Weijun Gao; Yingjun Ruan. 2018. "Quantifying variabilities and impacts of massive photovoltaic integration in public power systems with PHS based on real measured data of Kyushu, Japan." Energy Procedia 152, no. : 883-888.
Due to high variability of energy demand in a whole year, optimizing the configuration and operation of a CCHP system will take very high and unfeasible computational time expenses. To overcome this problem, this paper presents a new and creative method to get few representative days that adequately preserve significant demand characteristics. Typical demand days are selected based on the use of k-means clustering algorithm and average method. A hypothetical CCHP system is optimized with mixed-integer linear programming algorithm (MILP) in order to confirm the selection of typical days in this paper. This paper also imitates traditional method. A case study of a Qingdao office building is discussed to demonstrate the proposed method. The results illustrate that the magnitude of Mean Absolute Percentage Errors (MAPE) between actual demand load and typical days load can affect actual operational effect. In conclusion, optimal number of typical days for actual CCHP operation can obtain very low MAPE and lowest annual total cost.
Yuan Gao; Qianying Liu; Shuxia Wang; Yingjun Ruan. Impact of typical demand day selection on CCHP operational optimization. Energy Procedia 2018, 152, 39 -44.
AMA StyleYuan Gao, Qianying Liu, Shuxia Wang, Yingjun Ruan. Impact of typical demand day selection on CCHP operational optimization. Energy Procedia. 2018; 152 ():39-44.
Chicago/Turabian StyleYuan Gao; Qianying Liu; Shuxia Wang; Yingjun Ruan. 2018. "Impact of typical demand day selection on CCHP operational optimization." Energy Procedia 152, no. : 39-44.
There are many problems of central heating system in China: low efficiency, inadequate regulation function, serious thermal imbalance and excessive heating. Due to these problems, energy-saving work of central heating system is particularly important. The operation strategy of the heating system and the accurate adaption of heating demand will directly affect the energy consumption. Based on the heating load, the corresponding heat supply system and the specific equipment are established into a mathematical model, and the operation characteristics of the compound heating system is optimized by genetic algorithm. The result shows that the heating load ratio of heat pump units increases gradually with the increase of outdoor temperature, when the outdoor temperature is higher than 5℃, the heat pump units bears the heat load alone in Qingdao city. Its COP is affected by outdoor temperature and partial load rate. The steam consumption is related to the supply and return water temperature of the network. We propose a method to achieve the lowest operating cost of compound heating system by optimizing the supply and return water temperature and circulating water flow. Optimization result contains reasonable supply and return water temperature, appropriate load bearing ratio of heat pump units, which can effectively reduce the steam consumption. Compound energy system can improve the matching relation between heat supply and heating load, because the heat pump connected to the secondary network can improve the supply and return water temperature. Heat pump units will save 20% to 30% of operating cost when heating alone.
Chengkuan Fang; Qiang Xu; Shuxia Wang; Yingjun Ruan. Operation optimization of heat pump in compound heating system. Energy Procedia 2018, 152, 45 -50.
AMA StyleChengkuan Fang, Qiang Xu, Shuxia Wang, Yingjun Ruan. Operation optimization of heat pump in compound heating system. Energy Procedia. 2018; 152 ():45-50.
Chicago/Turabian StyleChengkuan Fang; Qiang Xu; Shuxia Wang; Yingjun Ruan. 2018. "Operation optimization of heat pump in compound heating system." Energy Procedia 152, no. : 45-50.
The increasing penetration of renewable energy decreases grid flexibility; thus, decentralized energy management or demand response are emerging as the main approaches to resolve this limitation and to provide flexibility of resources. This research investigates the performance of high energy efficiency appliances and grid-integrated distributed generators based on real monitored data from a social demonstration project. The analysis not only explores the potential cost savings and environmental benefits of high energy efficiency systems in the private sector, but also evaluates public grid load leveling potential from a bottom-up approach. This research provides a better understanding of the behavior of high decentralized efficient energy and includes detailed scenarios of monitored power generation and consumption in a social demonstration project. The scheduled heat pump effectively lifts valley load via transforming electricity to thermal energy, its daily electricity consumption varies from 4 kWh to 10 kWh and is concentrated in the early morning over the period of a year. Aggregated vehicle to home (V2H) brings flexible resources to the grid, by discharging energy to cover the residential night peak load, with fuel cost savings attributed to 90% of profit. The potential for grid load leveling via integrating the power utility and consumer is examined using a bottom-up approach. Five hundred thousand contributions from scheduled electrical vehicles (EVs) and fuel cells provide 5.0% of reliable peak power capacity at 20:00 in winter. The outcome illustrates the energy cost saving and carbon emission reduction scenarios of each of the proposed technologies. Relevant subsidies for heat pump water heater systems and cogeneration are essential customers due to the high initial capital investment. Optimal mixes in structure and coordinated control of high efficiency technologies enable customers to participate in grid load leveling in terms of lowest cost, considering their different features and roles.
Yanxue Li; Weijun Gao; Yingjun Ruan; Yoshiaki Ushifusa. Grid Load Shifting and Performance Assessments of Residential Efficient Energy Technologies, a Case Study in Japan. Sustainability 2018, 10, 2117 .
AMA StyleYanxue Li, Weijun Gao, Yingjun Ruan, Yoshiaki Ushifusa. Grid Load Shifting and Performance Assessments of Residential Efficient Energy Technologies, a Case Study in Japan. Sustainability. 2018; 10 (7):2117.
Chicago/Turabian StyleYanxue Li; Weijun Gao; Yingjun Ruan; Yoshiaki Ushifusa. 2018. "Grid Load Shifting and Performance Assessments of Residential Efficient Energy Technologies, a Case Study in Japan." Sustainability 10, no. 7: 2117.