Soon-Thiam Khu

An Investigation on Preference Order Ranking Scheme for Multiobjective Evolutionary Optimization

It may be generalized that all Evolutionary Algorithms (EA) draw their strength from two sources: exploration and exploitation. Surprisingly, within the context of multiobjective (MO) optimization, the impact of fitness assignment on the exploration-exploitation balance has drawn little attention. The vast majority of multiobjective evolutionary algorithms (MOEAs) presented to date resort to Pareto dominance classification as a fitness assignment methodology. However, the proportion of Pareto optimal elements in a set P grows with the dimensionality of P. Therefore, when the number of objectives of a multiobjective problem (MOP) is large, Pareto dominance-based ranking procedures become ineffective in sorting out the quality of solutions. This paper investigates the potential of using preference order-based approach as an optimality criterion in the ranking stage of MOEAs. A ranking procedure that exploits the definition of preference ordering (PO) is proposed, along with two strategies that make different use of the conditions of efficiency provided, and it is compared with a more traditional Pareto dominance-based ranking scheme within the framework of NSGA-II. A series of extensive experiments is performed on seven widely applied test functions, namely, DTLZ1, DTLZ2, DTLZ3, DTLZ4, DTLZ5, DTLZ6, and DTLZ7, for up to eight objectives. The results are analyzed through a suite of five performance metrics and indicate that the ranking procedure based on PO enables NSGA-II to achieve better scalability properties compared with the standard ranking scheme and suggest that the proposed methodology could be successfully extended to other MOEAs

Multiple objective optimal control of integrated urban wastewater systems

Integrated modelling of the urban wastewater system has received increasing attention in recent years and it has been clearly demonstrated, at least at a theoretical level, that system performance can be enhanced through optimized, integrated control. However, most research to date has focused on simple, single objective control. This paper proposes consideration of multiple objectives to more readily tackle complex real world situations. The water quality indicators of the receiving water are considered as control objectives directly, rather than by reference to surrogate criteria in the sewer system or treatment plant. A powerful multi-objective optimization genetic algorithm, NSGA II, is used to derive the Pareto optimal solutions, which can illustrate the whole trade-off relationships between objectives. A case study is used to demonstrate the benefits of multiple objective control and a significant improvement in each of the objectives can be observed in comparison with a conventional base case scenario. The simulation results also show the effectiveness of NSGA II for the integrated urban wastewater system despite its complexity.

A hybrid genetic algorithm for the design of water distribution networks

Genetic algorithms are currently one of the state-of-the-art techniques for the optimisation of engineering systems including water network design and rehabilitation. They are capable of finding near optimal cost solutions to these problems given certain cost and hydraulic parameters. However, many forms of genetic algorithms rely on random starting points that are often poor solutions and the problem of how to efficiently provide good initial estimates of solution sets automatically is still an ongoing research topic. This paper proposes a novel method, known as CANDA-GA, which uses a heuristic-based, local representative cellular automata approach to provide a good initial population for genetic algorithm runs. CANDA-GA is applied to three networks, one taken from the literature and two taken from industry. The results show that the proposed method consistently outperforms the conventional non-heuristic-based GA approach in terms of producing more economically designed water distribution networks.

Efficient multi-objective optimal design of water distribution networks on a budget of simulations using hybrid algorithms

The design of water distribution networks is a large-scale combinatorial, non-linear optimisation problem, involving many complex implicit constraint sets, such as nodal mass balance and energy conservation, which are commonly satisfied through the use of hydraulic network solvers. These problem properties have motivated several prior studies to use stochastic search optimisation, because these derivative-free global search algorithms have been shown to obtain higher quality solutions for large network design problems. Global stochastic search methods, however, require many iterations to be performed in order to achieve a satisfactory solution, and each iteration may involve running computationally expensive simulations. Recently, this problem has been compounded by the evident need to embrace more than a single measure of performance into the design process, since by nature multi-objective optimisation methods require even more iterations. The use of metamodels as surrogates for the expensive simulation functions has been investigated as a possible remedy to this problem. However, the identification of reliable surrogates is not always a viable alternative. Under these circumstances, methods that are capable of achieving a satisfactory level of performance with a limited number of function evaluations represent a valuable alternative. This paper represents a first step towards filling this gap. Two recently introduced multi-objective, hybrid algorithms, ParEGO and LEMMO, are tested on the design problem of a real medium-size network in Southern Italy, and a real large-size network in the UK under a scenario of a severely restricted number of function evaluations. The results obtained suggest that the use of both algorithms, in particular LEMMO, could be successfully extended to the efficient design of large-scale water distribution networks.

An integrated model for water management in a rapidly urbanizing catchment

Existing water and environmental management models usually separately simulate socio-economic, water infrastructure and natural receiving water systems and thus cannot effectively capture the interactions among economic and population growth, water resource supply and depletion as well as environmental changes, especially in analyzing long-term scenarios of urbanization. In this paper, a system dynamics and water environmental model (SyDWEM) was developed to improve the understanding of the integrated socio-economic and water management system in a rapidly urbanizing catchment. The integrative character of SyDWEM is featured by putting the socio-economic component as an internal sub module of the whole system. It also contains water consumption and pollution load module, water supply module, wastewater treatment module as well as receiving water module. The Shenzhen River catchment was used as a case study to demonstrate usage of the functionality and purpose of the integrated model. The results indicate that SyDWEM has the capacity to predict the socio-economic and environment changes at a catchment scale under proposed socio-economic policies and water infrastructure planning. Therefore, it can help support the integration of decision making in socio-economic development and environment management.

An efficient algorithm for sensor placement in water distribution systems

The objective of this paper is to present an optimal sensor placement methodology to assist in the effective and efficient detection of accidental and/or intentional contaminant intrusion(s) in water distribution systems. The work presented here is done in response to call for papers for the Battle of the Water Sensors Networks (BWSN), at the Water Distribution Systems Analysis Symposium (2006). The above problem is formulated and solved as a constrained multiobjective optimisation problem. The four objectives are: (1) minimisation of the expected time of detection, (2) minimisation of the expected population affected prior to detection, (3) minimisation of the expected demand of contaminated water prior to detection and (4) maximisation of the detection likelihood. The constraint modelled is the pre-specified number of detection sensors used in the sampling design. Decision variables are the sensor network locations. The solution methodology proposed is based on the novel Noisy Cross-Entropy Sensor Locator (nCESL) algorithm. This algorithm is applied to the two competition networks under four base contamination scenarios (A, B, C and D) and two different numbers of sensors available (5 and 20). The results obtained demonstrate the effectiveness and efficiency of the sensor placement methodology proposed. Copyright ASCE 2006.

A novel cellular automata based approach to storm sewer design

Optimal storm sewer design aims at minimizing capital investment on infrastructure whilst ensuring good system performance under specified design criteria. An innovative sewer design approach based on cellular automata (CA) principles is introduced in this paper. Cellular automata have been applied as computational simulation devices in various scientific fields. However, some recent research has indicated that CA can also be a viable and efficient optimization engine. This engine is heuristic and largely relies on the key properties of CA: locality, homogeneity, and parallelism. In the proposed approach, the CA-based optimizer is combined with a sewer hydraulic simulator, the EPA Storm Water Management Model (SWMM). At each optimization step, according to a set of transition rules, the optimizer updates all decision variables simultaneously based on the hydraulic situation within each neighbourhood. Two sewer networks (one small artificial network and one large real network) have been tested in this study. The CA optimizer demonstrated its ability to obtain near-optimal solutions in a remarkably small number of computational steps in a comparison of its performance with that of a genetic algorithm.

Spatial variations of storm runoff pollution and their correlation with land-use in a rapidly urbanizing catchment in China

The composition of land use for a rapidly urbanizing catchment is usually heterogeneous, and this may result in significant spatial variations of storm runoff pollution and increase the difficulties of water quality management. The Shiyan Reservoir catchment, a typical rapidly urbanizing area in China, is chosen as a study area, and temporary monitoring sites were set at the downstream of its 6 sub-catchments to synchronously measure rainfall, runoff and water quality during 4 storm events in 2007 and 2009. Due to relatively low frequency monitoring, the IHACRES and exponential pollutant wash-off simulation models are used to interpolate the measured data to compensate for data insufficiency. Three indicators, event pollutant loads per unit area (EPL), event mean concentration (EMC) and pollutant loads transported by the first 50% of runoff volume (FF50), were used to describe the runoff pollution for different pollutants in each sub-catchment during the storm events, and the correlations between runoff pollution spatial variations and land-use patterns were tested by Spearmans rank correlation analysis. The results indicated that similar spatial variation trends were found for different pollutants (EPL or EMC) in light storm events, which strongly correlate with the proportion of residential land use; however, they have different trends in heavy storm events, which correlate with not only the residential land use, but also agricultural and bare land use. And some pairs of pollutants (such as COD/BOD, NH(3)-N/TN) might have the similar source because they have strong or moderate positive spatial correlation. Moreover, the first flush intensity (FF50) varies with impervious land areas and different interception ratio of initial storm runoff volume should be adopted in different sub-catchments.

A novel evolutionary meta-heuristic for the multi-objective optimization of real-world water distribution networks

Genetic algorithms are currently one of the state-of-the-art meta-heuristic techniques for the optimization of large engineering systems such as the design and rehabilitation of water distribution networks. They are capable of finding near-optimal cost solutions to these problems given certain cost and hydraulic parameters. Recently, multi-objective genetic algorithms have become prevalent in the water industry due to the conflicting nature of these hydraulic and cost objectives. The Pareto-front of solutions can aid decision makers in the water industry as it provides a set of design solutions which can be examined by experienced engineers. However, multi-objective genetic algorithms tend to require a large number of objective function evaluations to arrive at an acceptable Pareto-front. This article investigates a novel hybrid cellular automaton and genetic approach to multi-objective optimization (known as CAMOGA). The proposed method is applied to two large, real-world networks taken from the UK water industry. The results show that the proposed cellular automaton approach can provide a good approximation of the Pareto-front with very few network simulations, and that CAMOGA outperforms the standard multi-objective genetic algorithm in terms of efficiency in discovering similar Pareto-fronts.

Optimal Distribution and Control of Storage Tank to Mitigate the Impact of New Developments on Receiving Water Quality

Storage tanks are commonly installed in a combined sewer system to control the discharge of combined sewer overflows that have been identified as a leading source for receiving water pollution. The traditional approach to determine the distribution of storage tank volume in the sewer system is confined to the use of objectives within the system itself due to the limits of separate modeling of urban wastewater systems, consisting of the sewer system, wastewater-treatment plant, and receiving water. The aim of this study is to investigate the optimal distribution and control of storage tanks with an objective to mitigate the impact of new residential development on receiving water quality from an integrated modeling perspective. An integrated urban wastewater model has been used to test three optimization scenarios: optimal flow rate control, storage distribution, and a combination of these two. In addition to the cost of storage tank construction, two receiving water quality indicators, dissolved oxygen and ammonium concentration, are used as optimization objectives. Results show the benefits of direct evaluation of receiving water quality impact in the context of storage distribution optimization. Results indicate that storage allocation should be considered in conjunction with optimal flow rate control to achieve the maximum effectiveness in water pollution mitigation.