GRU-integrated constrained soft actor-critic learning enabled fully distributed scheduling strategy for residential virtual power plant

In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-integrated DRL algorithm guides the RVPP to participate effectively in both the day-ahead and real-time markets,lowering the electricity purchase costs and consumption risks for end-users.The Lagrangian relaxation technique is introduced to transform the constrained Markov decision process(CMDP)into an unconstrained optimization problem,which guarantees that the constraints are strictly satisfied without determining the penalty coefficients.Furthermore,to enhance the scalability of the constrained soft actor-critic(CSAC)-based RVPP scheduling approach,a fully distributed scheduling architecture was designed to enable plug-and-play in the residential distributed energy resources(RDER).Case studies performed on the constructed RVPP scenario validated the performance of the proposed methodology in enhancing the responsiveness of the RDER to power tariffs,balancing the supply and demand of the power grid,and ensuring customer comfort.

Optimal dispatching strategy for residential demand response considering load participation

To facilitate the coordinated and large-scale participation of residential flexible loads in demand response(DR),a load aggregator(LA)can integrate these loads for scheduling.In this study,a residential DR optimization scheduling strategy was formulated considering the participation of flexible loads in DR.First,based on the operational characteristics of flexible loads such as electric vehicles,air conditioners,and dishwashers,their DR participation,the base to calculate the compensation price to users,was determined by considering these loads as virtual energy storage.It was quantified based on the state of virtual energy storage during each time slot.Second,flexible loads were clustered using the K-means algorithm,considering the typical operational and behavioral characteristics as the cluster centroid.Finally,the LA scheduling strategy was implemented by introducing a DR mechanism based on the directrix load.The simulation results demonstrate that the proposed DR approach can effectively reduce peak loads and fill valleys,thereby improving the load management performance.

Conservation and Renewal Strategies of Industrial Heritage Residential Areas from the Perspective of Heritage Protection : A Case Study of Residential Area of Wuchang Vehicle Factory

The residential area of Wuchang Vehicle Factory is taken as a case to explore the protection and renewal strategies of industrial heritage residential areas.By analyzing the current situation of the residential area,issues such as functional decline,memory loss,and weakened community vitality are revealed.Three design concepts are proposed:building renovation,historical space renovation,and the introduction of cultural and creative industries,aiming to improve the living environment,showcase historical value,cultivate cultural and creative industries,promote economic transformation,and community vitality.This paper could provide reference for the protection and renewal of similar industrial heritage residential areas,and new ideas for the research and utilization of industrial heritage.By comprehensively considering heritage protection,cultural inheritance,and community development,systematic suggestions are proposed.

MAQMC:Multi-Agent Deep Q-Network for Multi-Zone Residential HVAC Control

The optimization of multi-zone residential heating,ventilation,and air conditioning(HVAC)control is not an easy task due to its complex dynamic thermal model and the uncertainty of occupant-driven cooling loads.Deep reinforcement learning(DRL)methods have recently been proposed to address the HVAC control problem.However,the application of single-agent DRL formulti-zone residential HVAC controlmay lead to non-convergence or slow convergence.In this paper,we propose MAQMC(Multi-Agent deep Q-network for multi-zone residential HVAC Control)to address this challenge with the goal of minimizing energy consumption while maintaining occupants’thermal comfort.MAQMC is divided into MAQMC2(MAQMC with two agents:one agent controls the temperature of each zone,and the other agent controls the humidity of each zone)and MAQMC3(MAQMC with three agents:three agents control the temperature and humidity of three zones,respectively).The experimental results showthatMAQMC3 can reduce energy consumption by 6.27%andMAQMC2 by 3.73%compared with the fixed point;compared with the rule-based,MAQMC3 andMAQMC2 respectively can reduce 61.89%and 59.07%comfort violation.In addition,experiments with different regional weather data demonstrate that the well-trained MAQMC RL agents have the robustness and adaptability to unknown environments.

An Extended Fuzzy-DEMATEL System for Factor Analyses on Social Capital Selection in the Renovation of Old Residential Communities

China has been promoting the renovation of old residential communities vigorously.Due to the financial pressure of the government and the sustainability of the renovation of old residential communities,public-private partnerships(PPP)have already gained attention.The selection of social capital is key to improving the efficiency of the PPP model in renovating old residential communities.In order to determine the influencing factors of social capital selection in the renovation of old residential communities,this paper aims to find an effective approach and analyze these factors.In this paper,a fuzzy decision-making and trial evaluation laboratory(fuzzy-DEMATEL)technique is extended and amore suitable systemis developed for the selection of social capital using the existing group decisionmaking theory.In the first stage,grounded theory is used to extract the unabridged key influencing factors for social capital selection in the renovation of old residential communities.Secondly,by considering the impact of expert weights,the key influencing factors are identified.The interactions within these influencing factors are discussed and the credibility of the results is verified by sensitivity analysis.Finally,these key influencing factors are sorted by importance.Based on the results,the government should focus on a technical level,organizationalmanagement abilities,corporate reputation,credit status,etc.This study provides the government with a theoretical basis and a methodology for evaluating social capital selection.

Optimization of Green Space Plant Configuration in Residential Areas of Chongqing Central Business District Based on Green Plot Ratio—A Case Study of Xuhui City Residential Community

The current urban green space construction was guided by a two-dimensional index evaluation system, resulting in weak ecological benefits of green space. Green plot ratio (GPR), as a three-dimensional indicator, can characterize the ecological benefits of green areas and the ability of green areas to participate in the operation and regulation of urban ecosystems. As an important component of urban green space, the GPR index was added to the two-dimensional index evaluation system to optimize the green space, which can promote the development of low-carbon, healthy and ecological green space. Based on the research of 22 residential districts in the central city of Chongqing, the Leaf area index (LAI) index of common native garden plants in Chongqing was formed to improve the accuracy of green capacity index measurement in Chongqing. The study also took the residential community of Sunrise City in Banan District of Chongqing as an example, and carried out the optimization design practice from four types of residential community green areas: green areas next to houses, road green areas, concentrated green areas, and green areas attached to public service facilities.

Multi-subject and multi-objective integrated optimization system and implementation strategy for energy-saving renovation of the existing residential buildings

The core of the healthy and orderly operation of the existing residential building energy-saving renovation market lies in the exploration of the implementation mechanism of multi-subject and multi-objective integrated optimization.The multi-agent and multi-objective integrated optimization system framework is a powerful tool to guide the scientific decision-making of the market core structural entities in the future market practice. This paper analyzes the practical dilemma of energy-saving renovation of theexisting residential buildings in China, summarizes the practical experience of multi-subject and multi-objective integrated optimization of energy-saving renovation of the existing residential buildings in foreign countries, and puts forward beneficial practical enlightenment on the basis of comparison at home and abroad;The design principles of the target integrated optimization system have established a multi-subject and multi-objective integrated optimization system framework for the energy-saving renovation of the existing residential buildings, from six aspects: government guidance, trust consensus, value co-creation, risk sharing, revenue sharing, and social responsibility sharing. This paper proposes a multi-subject and multi-objective integrated practice strategy, in order to promote the efficient and orderly development of China's existing residential building energy-saving renovation market.

Research on the Spatial Characteristics of Traditional Residential Buildings in Ningxia Region

This article takes traditional residential buildings in Ningxia region as the starting point,and through field research and data analysis,demonstrates the specific elements of the spatial composition of traditional residential buildings and the common forms of courtyard space.The study summarizes the regional cultural characteristics of traditional residential buildings in the region,laying a foundation for subsequent research and providing some reference basis.

Residential Differentiation Based on Reachability and Spatial Clustering : A Case Study of the Main Urban Area of Wuhan City

The differentiation of urban residential space is a key and hot topic in urban research, which has very important theoretical significance for urban development and residential choice. In this paper, web crawler technology is used to collect urban big data. Using spatial analysis and clustering, the differentiation law of residential space in the main urban area of Wuhan is revealed. The residential differentiation is divided into five types: "Garden" community, "Guozi" community, "Wangjiangshan" community, "Yashe" community, and "Shuxin" community. The "Garden" community is aimed at the elderly, with good medical accessibility and open space around the community. The "Guozi Community" is aimed at young people, and the community has accessibility to good educational and commercial facilities. The "Wangjiangshan" community is oriented towards the social elite group, with beautiful natural living environment, close to the city core, and convenient transportation. The "Yashe" community is aimed at the general income group, and its location is characterized by being adjacent to commercial districts and convenient transportation. The "Shuxin" community is aimed at the middle and lower income groups, far from the city center, and the living environment quality is not high.

Perception of the Residential Environmental Quality of Yenagoa Metropolis,Nigeria

Residential environmental quality(REQ)affects human health and quality of life(QoL).Therefore,this study as­sessed residents’perception of the REQ of the Yenagoa metropolis.Data for the study were sourced from the 400 ad­ministered questionnaires,which required respondents to rate their REQ based on seven selected indicators(air quality,drinking water quality,housing location,sanitation,waste management,housing accessibility and noise pollution).The respondents were sampled using the multistage sampling technique.The data were analyzed using frequency,percent­age,t-test,ANOVA and REQ model.The findings show that the overall calculated REQ of Yenagoa was classified as“good quality”.The best-rated indicator was drinking water quality,while the least-rated was noise pollution.Ratings based on respondents’sex,income and educational status recorded similar results.Also,the respondents’perception of the REQ across the four zones was similar as the calculated ratings of all the zones fell under the“good quality”classification.Furthermore,the hypotheses tested revealed that there were no significant differences in the perception of the REQ by sex and income status,while significant variation exists by education status.Despite the general“good quality”rating,there is still room for improvement,especially in the areas of noise pollution,sanitation and housing location,which received relatively low ratings.

Residential environmental evaluation of local cities considering regional characteristic and personal residential preference—a case study of Saga City,Japan

Questionnaire surveys and subjective evaluations on residential environment were performed in order to grasp the main factors of residential environment of small local cities. The suitable evaluation index system was established, and the regional residential environment characteristics and personal residential preference types were analyzed, so that their influence on residential environment evaluation could be grasped. The results can be applied to the residential environment planning, construction and monitoring of local cities.

Residential Energy Scheduling for Variable Weather Solar Energy Based on Adaptive Dynamic Programming

The residential energy scheduling of solar energy is an important research area of smart grid. On the demand side, factors such as household loads, storage batteries, the outside public utility grid and renewable energy resources, are combined together as a nonlinear, time-varying, indefinite and complex system, which is difficult to manage or optimize. Many nations have already applied the residential real-time pricing to balance the burden on their grid. In order to enhance electricity efficiency of the residential micro grid, this paper presents an action dependent heuristic dynamic programming(ADHDP) method to solve the residential energy scheduling problem. The highlights of this paper are listed below. First,the weather-type classification is adopted to establish three types of programming models based on the features of the solar energy. In addition, the priorities of different energy resources are set to reduce the loss of electrical energy transmissions.Second, three ADHDP-based neural networks, which can update themselves during applications, are designed to manage the flows of electricity. Third, simulation results show that the proposed scheduling method has effectively reduced the total electricity cost and improved load balancing process. The comparison with the particle swarm optimization algorithm further proves that the present method has a promising effect on energy management to save cost.

Development of Temperature-Humidity Independent Control Air-Conditioning Unit for Residential Buildings

Cooling panels are increasingly used in domestic residential buildings.To provide medium temperature cold water for the cooling panel,and dehumidify the indoor air simultaneously,a new kind of temperature-humidity independent control air-conditioning unit was developed for single residential house by utilizing multi-variable technology.First,the supply air temperature was studied to determine the proper supply air flow rate for the humidity control.Then,the energy consumption of different temperature-humidity independent control systems was studied.The analysis indicates that unity evaporating temperature can be used to handle the moisture load and sensible heat load in two evaporators.So the unit scheme was put forward.Two evaporators were used to produce medium temperature water and dry air separately,and electric expansion valves were used to control the refrigerant distribution between the two evaporators.Then,experimental work was carried out to investigate the influence of compressor frequency,refrigerant distribution on the dehumidification capacity,energy efficiency and refrigeration capacity.In the end,the paper concludes that both compressor frequency and refrigerant distribution can control the dehumidification capacity,but the former influences the EER more than the latter,while the latter influences the refrigeration capacity more than the former.We can find a proper running point at certain sensible and latent cooling load by adjusting both compressor frequency and electric expansion valve.The energy consumption of this kind of unit was estimated and compared with present room air conditioners,which shows that it can save about 41% cooling energy consumption.

Analysis and forecast of residential building energy consumption in Chongqing on carbon emissions

Carbon emissions mainly result from energy consumption. Carbon emissions inevitably will increase to some extent with economic expansion and rising energy consumption. We introduce a gray theory of quantitative analysis of the energy consumption of residential buildings in Chongqing,China,on the impact of carbon emission factors. Three impacts are analyzed,namely per capita residential housing area,domestic water consumption and the rate of air conditioner ownership per 100 urban households. The gray prediction model established using the Chongqing carbon emission-residential building energy consumption forecast model is sufficiently accurate to achieve a measure of feasibility and applicability.

Emissions of volatile organic compounds and carbonyl compounds from residential coal combustion in China

Emissions of volatile organic compounds （VOCs） and carbonyls from residential coal combustion of five coals with different maturities were studied in a simulated room.The coals were burned in form of honeycomb briquettes in a domestic coal stove,one of the most common fuel/stove combinations in China.Through a dilution system,VOCs and carbonyls samples were collected by canisters and silica-gel cartridges and analyzed by gas chromatography and mass spectrum （GC/MS） and high performance liquid chromatography/ultraviolet （HPLC/UV）,respectively.The results show that the bituminous coals with medium volatile matter content produce the highest emissions while the anthracite yields the lowest.Among the identified carbonyls from the coal smoke,the aromatic compounds （benzaldehyde,2,5-dimethylbenzaldehyde and p-tolualdehyde,m/o-tolualdehyde,benzene,m,p-xylene and trimethyl-benzene） were relatively abundant,which might be due to the molecular structure of the coal.For formaldehyde,aromatic carbonyls and aliphatic alkanes,their concentrations increase up to the maximum values and then decrease with increasing coal maturity.The total carbonyls and VOCs have the same tendency,which was observed for the emission factors of organic carbon （OC）,elemental carbon （EC）,particulate matter （PM） and polycyclic aromatic hydrocarbons （PAHs） detected in the series study.

Effects of an Urban Park and Residential Area on the Atmospheric CO_2 Concentration and Flux in Seoul,Korea

The CO2 concentrations and fluxes over an urban forest site （Namsan） and an urban residential region （Boramae） in Seoul, Korea, during the non-growing season （2 4 March 2011）, the growing season （10-12 June 2011）, and the late-growing season （22-24 September 2011） were analyzed. The CO2 concentrations of two sites showed nearly the same diurnal variation, with a maximum value occurring during the night and a minimum value occurring during daytime, as well as the same seasonal variation, with a maximum value during the non-growing season （early spring） and a minimum value during the growing season （summer）. The CO2 flux over the urban forest did not show any typical diurnal variation during the non-growing season, but did show diurnal variation with a small positive value during the night and a large negative value during daytime in the growing and late-growing seasons due to photosynthesis in the urban forest. The CO2 flux over the urban residential region showed a positive daily mean value for all periods, with large values during the non-growing season and small values during the growing season, and it also showed diurnal variation with two maxima at 0600-1000 LST and 1800-2400 LST, and two minima at 0300-0600 LST and 1100-1500 LST, and was strongly correlated with the use of liquefied natural gas for cooking and heating by surrounding houses.

IMPACT OF CLIMATE ON SUMMER RESIDENTIAL ELECTRICITY CONSUMPTION IN HONG KONG

The influence of climatic variables and cooling degree days (CDD) on summer residential electricity consumption for the period 1980 through 1994 in Hong Kong was investigated. The association between Clo, a measure of amount of Clothing insulation to maintain comfort, and residential electricity consumption was also examined. Utilizing monthly data and multiple regression analyses, it is discovered vapor pressure was not significantly related to electricity consumption while Cloud cover was negatively associated with electricity use. Climatic variables, CDD and Clo provided highly comparable results in modeling summer residential electricity consumption. Mean temperature and Cloud gave the best result. Clo yielded a slightly higher R2 value (0.867) than that of CDD (0.865) in the models. These results indicated that Clo could replace the weather variables and CDD to model electricity consumption.

Decentralized Control for Residential Energy Management of a Smart Users' Microgrid with Renewable Energy Exchange

This paper presents a decentralized control strategy for the scheduling of electrical energy activities of a microgrid composed of smart homes connected to a distributor and exchanging renewable energy produced by individually owned distributed energy resources. The scheduling problem is stated and solved with the aim of reducing the overall energy supply from the grid, by allowing users to exchange the surplus renewable energy and by optimally planning users' controllable loads. We assume that each smart home can both buy/sell energy from/to the grid taking into account time-varying non-linear pricing signals. Simultaneously, smart homes cooperate and may buy/sell locally harvested renewable energy from/to other smart homes. The resulting optimization problem is formulated as a non-convex non-linear programming problem with a coupling of decision variables in the constraints. The proposed solution is based on a novel heuristic iterative decentralized scheme algorithm that suitably extends the Alternating Direction Method of Multipliers to a non-convex and decentralized setting. We discuss the conditions that guarantee the convergence of the presented algorithm. Finally, the application of the proposed technique to a case study under several scenarios shows its effectiveness.

Carbon Dioxide Concentration and Flux in an Urban Residential Area in Seoul,Korea

The carbon dioxide （CO2） concentrations and fluxes measured at a height of 17.5 m above the ground by a sonic anemometer and an open-path gas analyzer at an urban residential site in Seoul, Korea from February 2011 to January 2012 were analyzed. The annual mean CO2 concentration was found to be 750 mg m-3, with a maximum monthly mean concentration of 827 mg m-3 in January and a minimum value of 679 mg m-3 in August. Meanwhile, the annual mean CO2 flux was found to be 0.45 mg m-2 s-1, with a maximum monthly mean flux of 0.91 mg m-2 s-1 in January and a minimum value of 0.19 mg m-2 s-1 in June. The hourly mean CO2 concentration was found to show a significant diurnal variation; a maximum at 0700-0900 LST and a minimum at 1400-1600 LST, with a large diurnal range in winter and a small one in summer, mainly caused by diurnal changes in mixing height, CO2 flux, and surface complexity. The hourly mean CO2 flux was also found to show a significant diurnal variation, but it showed two maxima at 0700-0900 LST and 2100-2400 LST, and two minima at 1100-1500 LST and 0300-0500 LST, mainly caused by a diurnal pattern in CO2 emissions and sinks from road traffic, domestic heating and cooking by liquefied natural gas use, and the different horizontal distribution of CO2 sources and sinks near the site. Differential advection with respect to wind direction was also found to be a cause of diurnal variations in both the CO2 concentration and flux.

Spatial Modeling of Residential Crowding in Alexandria Governorate, Egypt: A Geographically Weighted Regression (GWR) Technique

Despite growing research for residential crowding effects on housing market and public health perspectives, relatively little attention has been paid to explore and model spatial patterns of residential crowding over space. This paper focuses upon analyzing the spatial relationships between residential crowding and socio-demographic variables in Alexandria neighborhoods, Egypt. Global and local geo-statistical techniques were employed within GIS-based platform to identify spatial?variations of residential crowding determinates. The global ordinary least squares (OLS) model?assumes homogeneity of relationships between response variable and explanatory variables?across the study area. Consequently, it fails to account for heterogeneity of spatial relationships. Local model known as a geographically weighted regression (GWR) was also employed using the same?response variable and explanatory variables to capture spatial non-stationary of residential?crowding. A comparison of the outputs of both models indicated that OLS explained 74 percent of?residential crowding variations while GWR model explained 79 percent. The GWR improvedstrength of the model and provided a better goodness of fit than OLS. In addition, the findings of this analysis revealed that residential crowding was significantly associated with different structural measures particularly social characteristics of household such as higher education and illiteracy. Similarly, population size of neighborhood and number of dwelling rooms were found to have direct impacts on residential crowding rate. The spatial relationship of these measures distinctly varies over the study area.