3972-47449300University of Tlemcen Faculty of technology Department of hydraulic Proposal

3972-47449300University of Tlemcen
Faculty of technology
Department of hydraulic
Proposal:
38588952753995PhD student
Khaled Chorfi
0PhD student
Khaled Chorfi
30622141417955Supervisor:
Pr. Bekkouche Abdelmalek
00Supervisor:
Pr. Bekkouche Abdelmalek
Optimization of Water Resources Systems using an Artificial Intelligence approach

2017-2018
Overview
The vocabulary and discourse of water resource management have expanded vastly in recent years to include an array of new concepts and terminology, such as water security, water productivity, virtual water, and water governance. While the new conceptual lenses may generate insights that improve responses to the world’s water challenges, their practical use is often encumbered by ambiguity and confusion.

Industrialization, urbanization, agriculture and all human’s activities not only consume water but also affect environmental and human lives. We face an existential global crisis of water that the World Economic Forum identifies the lack of water governance as one of the primary factors contributing to the water crisis in the exam of the causes and drivers of a multitude of risks affecting global populations. In the hope that we satisfied our future water demands, the water resources professionals who have learned how to plan, design, build, and operate structures that increase the bene?ts people can obtain from the water resources, must emerge their comfort zones and to engage with politicians, decision Makers and those stakeholders with influencing power. CITATION Ale17 l 1036 (Alexander Lane, Michael Norton, Sandra Ryan, 2017) CITATION Cen17 l 1036 (Cengiz Kahraman, ?rem Uçal Sar?, 2017) CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )To put it another way, the integrated water management which is one of the modern water management approaches, is a multi-dimensional process pivoted around the need for water, the policy to meet the needs and the management to implement the policy. The new models of integrated water resources management are required to address complex multi?stakeholder demand patterns and water?related responsibilities as a result of the grasp of the moment by water resources professionals to put themselves at the centre of the often?siloed disciplines of science, technology, politics, environment and economics. CITATION Cen17 l 1036 (Cengiz Kahraman, ?rem Uçal Sar?, 2017) CITATION Ale17 l 1036 (Alexander Lane, Michael Norton, Sandra Ryan, 2017).

Lyndon B Johnson in a letter to the President of the Senate and Speaker of the House in 1965, said:
‘A nation that fails to plan intelligently for the development and protection of its precious waters will be condemned to wither because of its short-sightedness. The Hard lessons of history are clear, written on the deserted sands and ruins of once proud civilizations.’
CITATION Ale17 l 1036 (Alexander Lane, Michael Norton, Sandra Ryan, 2017)Water is the most complex natural resource to manage, at the same time water in its cycle, both locally and globally, and through time makes it a unique natural resource. If we could imagine water as the complex system (“A system is an assemblage or combination of functionally related elements or parts forming a unitary whole” CITATION Ben11 l 1036 (Benjamin S. Blanchard, Wolter J. Fabrycky, 2011)) of fluxes that it is how we meet the challenge of water resources planning and management today, and will be an increasing challenge into the foreseeable future. The new Proposition of systems is to Improve understanding of the system to enable more rational allocation decisions. CITATION Ale17 l 1036 (Alexander Lane, Michael Norton, Sandra Ryan, 2017)The design of complex systems that appropriately incorporate optimization in the design process is an important challenge facing the systems engineer. The optimization is the process of seeking the best. In systems engineering and analysis, this process is applied to each alternative in accordance with the decision evaluation theory, with this in mind the optimization as a means to an end, not as an end in itself. CITATION Ben11 l 1036 (Benjamin S. Blanchard, Wolter J. Fabrycky, 2011)The complexity and nonlinearity of most earth and environmental problems have led to the increased use of computational intelligence techniques. The intelligent systems have important applications due to its ability to learn and keep up the changes of the previous activities on environment. Although developing an intelligence system is quite dif?cult because of the dynamic structure of the world, and the processes are dif?cult to represent, causing considerable uncertainty. CITATION Cen17 l 1036 (Cengiz Kahraman, ?rem Uçal Sar?, 2017)Originally, multi-agent systems came from the field of artificial intelligence (AI). At first, this field was called distributed artificial intelligence (DAI); instead of reproducing the knowledge and reasoning of one intelligent agent as in AI, the objective became to reproduce the knowledge and reasoning of several heterogeneous agents that need to coordinate to jointly solve planning problems. CITATION FBo04 l 1036 (F. Bousquet , C. Le Page, 2004)
Research questions
The last decades have seen a growing trend towards the water systems management, but the high complexity of interaction humans and water resources causing a difficult to represent the process. There is a need for better understanding and analysing of the water resources systems. More specifically, the flowing research question need to be addressed:
How to build the model for water resources systems on the principals of integrated water resources management?
How manage and analysis of relationships (interactions) humans-water resources?
How to classify the stakeholders and there important using of water resources?
What are the artificial intellige nce approaches as well as tools to optimize water resources systems?
The major approach
The study will conduct in the form of systems thinking to understand, manage, plane the water resources, in the second place, the intelligent system will be a contributing approach to optimize the water resources systems, whose contains many fields such as:
Neural networks: nonlinear input-output models inspired by brain processes.

Fuzzy systems: have the ability to realize a complex nonlinear input–output relation as a synthesis of multiple simple input–output relations.

Evolutionary algorithms: search and optimization algorithms that take their inspiration from natural selection and survival of the ?ttest in the biological world.

Tabu Search: based on procedures designed to cross boundaries of feasibility or local optimality, instead of treating them as barriers.

Particle swarm optimization: a biologically inspired computational search and optimization based on the social behaviours of birds ?ocking or ?sh schooling.

Ant colony optimization: metaheuristic approach for solving hard combinatorial optimization problems which is inspired by the foraging behaviour of ant colonies, and targets discrete optimization problems.

Bee Colony Optimization: new member of swarm intelligence inspired by bees’ behaviour in the nature.

Agent and multi-agent systems: an agent is a computer system in environment that influences each other and the multi-agent system is multiple agent interactions.

In the same token a hybrid of this fields present an advantage to solve the problems.
Significance of the research
Recent trends in water resources management have led to a proliferation of studies that recognize the high complexity of water resources systems. Those studies promote an important modelling possibility of water resources systems, which represents an essential component of the water resources management and planning process, and to reduce potential failures in the future.
There are several applications of intelligent techniques on environmental problems, but as it is seen from the literature review, most of the conventional modelling frameworks have not been integrated with intelligent techniques yet. In this research we propose a new application of intelligent techniques to optimize the water resources systems. CITATION Cen17 l 1036 (Cengiz Kahraman, ?rem Uçal Sar?, 2017)Positioning of the research
What we know about water resources systems is largely based upon analyst understanding of these systems. Daniel P. (2017) shows systems modelling difficulty in water resources systems field:
“Water resource systems are typically far more complex than what analysts can model and simulate. The reason is not primarily due to computational limitations but rather it is because we do not understand suf?ciently the multiple interdependent physical, biochemical, ecological, social, legal, and political (human) processes that govern the behavior of such water resource systems.”
CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )This concept has been challenged by X studies demonstrating
Recently, one of the most significant current discussions in water resources systems is why we use the systems thinking? the problem has received the scant attention of John E. Gibson, and he said:
“To engage systems thinking, we believe that the analyst needs to see the world with new eyes—that of a “systems perspective.” Much of the present literature in the area of systems analysis and systems engineering is very good; however, many sources fail to convey the art of systems problem-solving (systems analysis) by focusing instead on either operation research method (mathematical models such as linear programming) or formal Systems Engineering.”
CITATION Joh07 l 1036 (John E. Gibson, William T. Scherer, William F., 2007)This thought was Alexander Lane’s area of interest, and he introduces a new framework analysis water resources systems:
“New Water Architecture is a systems?based framework of conceptual, institutional and physical integration that builds on the principles of IWRM.
(……)
While what we are describing as New Water Architecture can be framed in systems-thinking language, we have chosen instead to use ‘connectivity’ and ‘integration’ as words to underpin the description of the approach. We envisage three levels of integration physical (focused on optimising water infrastructure); institutional (focused On improving water governance); and conceptual (focused on our collective mind-set and Attitude towards water).”
CITATION Ale17 l 1036 (Alexander Lane, Michael Norton, Sandra Ryan, 2017)This indicates a need to understand the various perceptions of water resources systems that exist among environmental engineering, economics, political, cultural and social, with a special focus on economic and social interactions, because they play a major part in the dynamics of the system. The use of this need by the modeler requisites mathematical and systems modeling skills. CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 ) CITATION SFe03 l 1036 (S. Feuillette, F. Bousquet, P. Le Goulven , 2003 ). On the other hand, the loss of the whole point is the result of the use of system analysis mathematics separated from the client’s real-world. CITATION Joh07 l 1036 (John E. Gibson, William T. Scherer, William F., 2007)Although the complex analytical techniques with computer programs that simulate the behaviour of water resource systems with mathematical principals are the base of developing of water resources modelling tools, developing models is an art which requires knowledge of the system being modeled, the client’s objectives, goals, and information needs. CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )The models in water resources field can be classified into three (03) types: CITATION SFe03 l 1036 (S. Feuillette, F. Bousquet, P. Le Goulven , 2003 )physical models centred on the dynamics of resources and that consider demand as a given parameter;
demand and that attempt to adapt water demand to a fixed amount of resource;
mixed models that represent interaction between the functioning of physical and socio-economic systems;
The probabilistic component, the time instant to be simulated and its impact on the behaviour of the system define the specific system characteristics of simulation model classification types such as, static, dynamic, deterministic, stochastic, continuous or discrete. CITATION Mar17 l 1036 (Marlene Amorim, Carlos Ferreira, Milton Vieira Junior, Carlos Prado, 2017)In addition, Optimization methods not only reduce the number for simulation analyses, but also maximize the index of performance with is a basic characteristic in system analysis through the identification of the critical parameters of the problem and calculation of their optimum setting. CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 ) CITATION Joh07 l 1036 (John E. Gibson, William T. Scherer, William F., 2007)The multi-agent systems as field of artificial intelligence showed good performance in optimization algorithms for solving hard problems CITATION Xia15 l 1036 (Xiao-long Zheng, Ling Wang, 2015).
The use of multi-agent systems in water resources systems is in keeping with what is being done in other fields because more industries are looking for ways to use multi-agent systems, indicating that agent technologies are making good progress in commercial use. CITATION Jin17 l 1036 (Jing Xie, Chen-Ching Liu, 2017)The aim of this research is to analysis with new-eyes based on systems thinking and optimize using artificial intelligence the water resources systems with an attempt to avoid failures and to address existing gaps, such us:
failures in water resources management because water has been and still is viewed as a free good; CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )the gaps in knowledge include the behavioral economics and political science of how water is actually allocated in practice, the long-term socioeconomic effects of water investments and policy choices, prediction and valuation of ecological responses to alternative water use, flow, and investment regimes, feedback effects of water use on local hydrology and hydrometeorology, Predicting the evolution of water demand. CITATION Cas15 l 1036 (Casey M. Brown, Jay R. Lund, Ximing Cai, Patrick M. Reed, Edith A. Zagona, Avi Ostfeld,Jim Hall, Gregory W. Characklis, Winston Yu, and Levi Brekke, 2015)the failure in distinguishing between the importance of system analysis tools as a product and the product which solving real-world problems in the service of real clients. CITATION Joh07 l 1036 (John E. Gibson, William T. Scherer, William F., 2007)The gap between what researchers in water resource systems modelling produce and publish, and what the practitioner ?nds useful and uses. CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )Furthermore, this project provided an important opportunity to answer the flowing questions if possible: CITATION Dan17 l 1036 (Daniel P. Loucks, Eelco van Beek, 2017 )” 1. How can these resources best be managed and used?
2. How can this be accomplished in an environment of uncertain and varying supplies and uncertain and increasing demands, and consequently of increasing con?icts among individuals having different interests in their management and use? “-48514025908000Planning
References
BIBLIOGRAPHY Alexander Lane, Michael Norton, Sandra Ryan. (2017). Water Resources : A New Water Architecture. (first, Ed.) Wiley Blacwell .

Benjamin S. Blanchard, Wolter J. Fabrycky. (2011). Systems engineering and analysis (5 th ed.). Prentice Hall .

Casey M. Brown, Jay R. Lund, Ximing Cai, Patrick M. Reed, Edith A. Zagona, Avi Ostfeld,Jim Hall, Gregory W. Characklis, Winston Yu, and Levi Brekke. (2015). The future of water resources systems analysis Toward a scientific framework for sustainable water management. American Geophysical Union., 6110-6124. doi:10.1002/2015WR017114
Cengiz Kahraman, ?rem Uçal Sar?. (2017). Intelligence Systems in Environmental Management Theory and Applications. Switzerland: Springer International Publishing. doi:10.1007/978-3-319-42993-9
Daniel P. Loucks, Eelco van Beek. (2017 ). Water Resource Systems Planning and Management : An Introduction to Methods, Models, and Applications. UNESCO-IHE, Springer .

Danny Weyns, H. Van Dyke Parunak, Fabien Michel, Tom Holvoet, Jacques Ferber. (2005). Environments for Multiagent Systems State-of-the-Art and Research Challenges. D. Weyns et al., 1–47.

F. Bousquet , C. Le Page. (2004). Multi-agent simulations and ecosystem management a review. Ecological Modelling , 176, 313–332. doi:10.1016/j.ecolmodel.2004.01.011
Jing Xie, Chen-Ching Liu. (2017). Multi-agent systems and their applications. Journal of International Council on Electrical Engineering, 188–197.

John E. Gibson, William T. Scherer, William F. (2007). HOW TO DO SYSTEMS ANALYSIS. New Jersey.: A JOHN WILEY & SONS, INC.

Marlene Amorim, Carlos Ferreira, Milton Vieira Junior, Carlos Prado. (2017). Engineering Systems and Networks The Way Ahead for Industrial Engineering and Operations Management. Switzerland: Springer. doi:10.1007/978-3-319-45748-2
O.I. Nkwonta , B. Dzwairo , F.A.O. Otieno , J.A. Adeyemo. (2017). A review on water resources yield model. south african journal of chemical engineering, 107-115. doi:10.1016/j.sajce.2017.04.002
S. Feuillette, F. Bousquet, P. Le Goulven . (2003 ). SINUSE a multi-agent model to negotiate water demand management on a free access water table. Environmental Modelling & Software, 413–427.

Xiao-long Zheng, Ling Wang. (2015). A multi-agent optimization algorithm for resource constrained project scheduling problem. Expert Systems with Applications.

Yi Xiao; Liping Fang; and Keith W. Hipel, Hon.D.WRE, F.ASCE. (2018). Agent-Based Modeling Approach to Investigating the Impact of Water Demand Management. Journal of Water Resources Planning and Management, 144(3). doi:10.1061/(ASCE)WR.1943-5452.0000907