Search

There has been a recent increase in the exploration of 'the discrete' in architecture, speculating on how an integrated approach to design, fabrication, assembly and inhabitation can disrupt the traditional investment- and decision-making models in the housing industry. Strategically designed part-to-whole systems allow for differentiation and reconfiguration, and the incorporation of different end-user' requirements. This potential of 'democratising' housing production requires further research into how the negotiation between multiple stakeholders' preferences can be guided through digital methods. This paper presents a research-by-design project that applies a digital and discrete material system to high-rise housing in Hong Kong, a typology which often features high degrees of standardisation. Through the development of an adaptable modular construction system and a multi-objective optimisation workflow, a system is explored that addresses the challenges of high-rise construction, and of customising high-density housing. The case study project demonstrates the ability of the workflow's evolutionary algorithm to balance complex requirements including maximising views, daylight access and internal connectivity according to diverse user requirements. [ABSTRACT FROM AUTHOR]

Zero-energy buildings usually achieve annual net-zero energy balance by generating electricity using on-site renewable energies and interconnecting with the power grid. However, the impact of energy mismatch problem in zero-energy buildings design on the grid is often overlooked, which potentially compromises grid's stability. To address this issue, this paper presents an optimization design method based on "grid-friendly interaction" which optimizes the energy system of zero-energy buildings to ensure better alignment between the building's electricity purchase/sale and grid demand. In this study, an indicator of "grid-friendly interaction", which represents the ratio of the net building friendly interaction power to the total annual interaction power, is firstly established to guide buildings in improving their interaction with the grid. Next, the energy supply, demand, and storage schemes of renewable energy systems in the zero-energy building are iteratively adjusted to achieve the best match with grid's expectations. This optimization design method was applied to a practical case in Hong Kong. Results show that, compared to the benchmark building, the optimal system design scheme increases grid friendliness by 83 %, reduces carbon dioxide emissions by 77 %, but also incurs a total cost increase of 180 %. The optimization design method proposed in this paper can effectively mitigate the impact of zero-energy buildings on the power grid, fostering enhanced interplay between the building structures and the grid. The study significantly contributes to the advancement of exploring the potential for energy flexibility in zero-energy buildings, which is of great significance for the safe and stable operation of future grids. The purpose of this study is to explore the energy flexibility potential of zero-energy buildings, which is of great significance for the safe and stable operation of future grids. • A novel indicator that reflects the degree of friendly interaction is proposed. • An optimization design method based on "grid-friendly interaction" is presented. • Single-objective and multi-objective optimization are applied respectively to ZCB. • It is of great significance for the safe and stable operation of future grids. [ABSTRACT FROM AUTHOR]

Clustering algorithms are applied to numerous problems in multiple domains including historic data analysis, financial markets analysis for portfolio optimization and image processing. Recent years have witnessed a surge in use of nature inspired computing (NIC) techniques for data clustering to solve various real world optimization problems. Granular Computing (GC) is an emerging technique to handle pieces of information, known as information granules. In this paper, an ensemble of fuzzy clustering using Particle Swarm Optimization and Granular computing for stock market portfolio optimization. The model is then tested on stocks listed in Hong Kong Stock Exchange. Experimental results suggested that clusters formed through Fuzzy Particle Swarm Optimization (FPSO) with Granular computing are well suited and efficient for portfolio optimization. For comparison, we have used a benchmark index of Hong Kong Stock Exchange called as Hang Sang Composite Index (HSCI). Results proved that results of proposed approach are better in comparison to benchmark results of HSCI. [ABSTRACT FROM AUTHOR]

This paper presents an optimization framework for adaptive scheduling of mixed bus services with flexible fleet size assignment under demand uncertainty. The service scheduling plans are driven by prevailing stochastic passenger demand subject to operational constraints. The optimization problem is formulated as a Markov decision process which aims to minimize passengers' in-vehicle and waiting times, as well as the operator's cost via use of services with different routes, schedules, and fleet sizes. To address the computational challenges, the solutions to the problem are to be calculated with use of reinforcement learning techniques. The proposed framework is implemented and tested using real-world scenarios configured from actual bus service route in Hong Kong. Experiment results reveals the benefits of the proposed bus service scheduling framework with use of flexible routes and fleet sizes in saving passengers' and operator's costs. This study contributes to real time transit operational planning with advanced computing and optimization techniques. • A dynamic bus network optimization model for flexible fleet, route, and schedule assignment. • A novel reinforcement learning based solution framework incorporating operational constraints. • A novel solution framework that can derive operational plans with multiple conflicting objectives. • A case study demonstrating the efficiency and practicality from both passengers' and operators' perspectives. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-population genetic algorithm (MPGA) program for wind turbine layout optimization in a wind farm which aims at extracting the maximum power in a minimum investment cost. The MPGA program is applied to a 2 km×2 km wind farm considering three different wind scenarios, i.e. (a): constant wind speed of 12 m/s with fixed wind direction; (b): constant wind speed of 12 m/s with variable wind direction and (c): variable wind speed of 8 m/s, 12 m/s, 17 m/s with variable wind directions. Compared with previous studies, the results of power generation cost of energy and wind farm efficiency are improved in the paper using MPGA which validate that MPGA works effectively in wind turbine layout optimization with wind farm. Additionally, a case study of wind turbine layout configuration op1timization using the MPGA program in a hypothetical offshore wind farm located in Hong Kong southeastern water is attempted using the 20 years׳ wind data from 1992 to 2011. The optimization result is beneficial for the assessment of the offshore wind power potential in Hong Kong. It is indicated that, under the optimization of wind turbines layout in the wind farm, 39.14×10 8 kWh/year electricity can be converted from the offshore wind farm, which occupies 9.09% of the 2012 electricity consumption in Hong Kong. Results show that the multi-population genetic algorithm program can be applied in any real-world wind farms for wind turbine layout optimization when the wind farm boundary is determined as well as the local wind condition is obtained. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive optimization framework for dynamic rail transit network operations with use of a rollout surrogate-approximate dynamic programming method. The optimization algorithm derives coordinated decisions of service schedules and train unit deployment with respect to prevailing passenger demand. Considering the computational effectiveness needed for real-time applications, a state-dependent surrogate function is incorporated to approximate the costs associated with operational decisions over future stages. The surrogate approximation is updated iteratively via a temporal difference learning process with feeding of observations made from the transit network. The proposed framework is implemented and tested on a real-world scenario in Hong Kong Light Rail Transit (LRT) network. The results reveal that the proposed framework is able to reduce significantly the total passengers' waiting times over existing plans with reasonable computational time via use of the surrogate approximation. This suggests the potential of the proposed optimizer for real time applications in large-scale rail transit networks. • A dynamic transit network optimization model for flexible train unit and schedule assignment. • A novel surrogate approximate dynamic programming with a cross-entropy solution framework. • A novel real-time solution framework with use of cross-entropy method incorporating state-dependent constraints. • A case study demonstrating the efficiency of the proposed framework for passengers in real-time. [ABSTRACT FROM AUTHOR]

Aggregate is one of the most widely used construction materials in the world. Due to its global extensive use, extracting and transporting the huge amounts of aggregate result in significant environmental impacts and economic burdens. Therefore, selecting aggregate supply sources with low environmental impacts and material cost has become important, particularly for the regions with limited local resources. This study presents an integrated model based on life cycle assessment and multi-objective optimization to plan the optimal aggregate supplies from different sources. The results can help stakeholders formulate sustainable material supply strategies that minimize the associated environmental impacts and material cost while meeting the demand and emission targets. As over 70% of the aggregates used in Hong Kong are imported across the border, the aggregate industry of Hong Kong is used to elaborate the model development and optimization in this paper. The results show that the use of locally-recycled aggregate should be encouraged as it is beneficial from both environmental and economic perspectives. However, due to the lacks of public perception and engineering experience, the annual supply and consumption of recycled aggregate are still very low (i.e., 0.3% market share). The local industry should overcome the application barriers and increase the supply capacity of recycled aggregate in order to maximize the environmental and economic benefits. Furthermore, use of locally-quarried aggregates can help achieve emission reduction targets, but at the expense of increased material cost. The acceptable emission targets in Hong Kong can be achieved under current aggregate production capacities, but medium and ambitious emission caps are too stringent and require substantial improvements in local aggregate supplies. It is suggested that material availability from various sources should be considered when formulating the reduction targets. [ABSTRACT FROM AUTHOR]

This paper describes the prediction of settlements induced by urban area tunneling using five machine learning (ML) algorithms. The settlement database, which was collected from a subway tunnel project in Hong Kong, consisted of 253 settlement measurements and 32 settlement influencing factors. The Bayesian optimization-based hyperparameter tuning was applied to efficiently explore optimal combinations and to enhance prediction performance. The optimal hyperparameters were selected by considering the three-fold cross-validation (CV) result of training data. The performance of the developed model was evaluated by comparing the root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) values. The extreme gradient boosting algorithm demonstrated the highest prediction accuracy with RMSE, MAE, and R2 values of 1.606, 1.331, and 0.835, respectively. • Tunneling-induced surface settlements predicted with five machine learning algorithms. • Bayesian optimization demonstrated excellent hyperparameter tuning search ability. • Prediction performance of trained models validated using three-fold cross-validation. • Consistency of prediction results validated with acceptable residual errors. • XGB model achieved the highest prediction performance with RMSE of 1.606. [ABSTRACT FROM AUTHOR]

The harmonic motion of pendulum swinging centered at a pivot point is mimicked in this work. The harmonic motion's amplitude at both side of the pivot are equal, damped, and decreased with time. This behavior is mimicked by the agents of the pendulum search algorithm (PSA) to move and look for an optimization solution within a search area. The high amplitude at the beginning encourages exploration and expands the search area while the small amplitude towards the end encourages fine-tuning and exploitation. PSA is applied for a vaccine distribution problem. The extended SEIR model of Hong Kong's 2009 H1N1 influenza epidemic is adopted here. The results show that PSA is able to generate a good solution that is able to minimize the total infection better than several other methods. PSA is also tested using 13 multimodal functions from the CEC2014 benchmark function. To optimize multimodal functions, an algorithm must be able to avoid premature convergence and escape from local optima traps. Hence, the functions are chosen to validate the algorithm as a robust metaheuristic optimizer. PSA is found to be able to provide low error values. PSA is then benchmarked with the state-of-the-art particle swarm optimization (PSO) and sine cosine algorithm (SCA). PSA is better than PSO and SCA in a greater number of test functions; these positive results show the potential of PSA. [ABSTRACT FROM AUTHOR]

LDAC (liquid desiccant air-conditioning system) is promising for reducing the energy consumption, and improving the indoor air quality. In this paper, the operation performance of LDAC with internally cooled/heated dehumidifier/regenerator was simulated and optimized. The cooling tower and solar collectors were employed as the cooling/heating source. Four nested iteration loops were developed and solved for system modeling. A typical commercial building in Hong Kong was selected as a case study, which air-conditioning load was obtained by Energy-plus. Results show that with the increase of solar collector area, the electricity consumption of AC (air-conditioning systems) system reduced by 11-35% in original system, but only a part of dehumidification demand was handled with liquid desiccant ventilation, which led to a low chiller COP (coefficient of performance). By adding a cooling coil for the solution entering dehumidifier, the electricity saving effectively increased to 22-47%, while the heat demand for regeneration also increased by 17%. So, a heat exchanger between water leaving regenerator and solution leaving dehumidifier was introduced. With the lower thermal requirement (reduced by 20%) and higher solar fraction (increased from 30 to 40%), the saving further increased to 29-49%, and the required collector area obviously reduced by 50-60% for the similar energy saving purpose. [ABSTRACT FROM AUTHOR]