CN-122022319-A - Multi-source-aware intelligent dynamic scheduling method and device for water supply network

CN122022319ACN 122022319 ACN122022319 ACN 122022319ACN-122022319-A

Abstract

The application provides a multi-source-aware intelligent water supply network dynamic scheduling method and device, relates to the technical field of water supply networks, and solves the problem that scheduling decisions are inaccurate due to the fact that water supply network scheduling lacks comprehensive utilization of multi-source and key data in the prior art. The method specifically comprises the steps of obtaining a water supply network data set, constructing a scheduling optimization problem based on the water supply network large data set, wherein the water supply network data set comprises pressure, flow rate, water source water level, electricity price and the like of nodes, solving the scheduling optimization problem by adopting a branch-and-bound method to obtain a mixed integer programming problem of discrete operation instruction sequences of the water pump in each period of a demodulation period, and generating an intelligent scheduling instruction sequence. The application is used for dynamic scheduling of the water supply network.

Inventors

LI WU
LI WEILONG
WU WEILE
XIONG GAOLI
YANG ZHIHE
LIU GANG
YI GAOFEI
HUANG DONG
ZHOU CHEN
YANG YING
FENG XIN

Assignees

湖南民族职业学院
湖南理工学院
湖南云河信息科技有限公司
湖南三湘四海水务有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A multi-source perceived water supply network dynamic scheduling method is characterized by comprising the following steps: Acquiring a water supply network data set, wherein the water supply network data set comprises the pressure, the flow rate, the water source water level and the electricity price of a node; constructing a scheduling optimization problem based on the water supply pipe network data set, wherein the scheduling optimization problem is a mixed integer programming problem of a discrete operation instruction sequence of the water pump in each period of demodulation period; and solving the scheduling optimization problem by adopting a branch-and-bound method to generate a scheduling instruction sequence.
2. The method of claim 1, wherein constructing a scheduling optimization problem based on the water supply network dataset comprises: Setting a discrete operation instruction sequence of the water pump as a decision variable; Constructing an objective function based on the economic running cost, the pressure stability penalty and the retention penalty; setting node pressure constraint, water level constraint and equipment operation constraint of the water supply network data set; and constructing a scheduling optimization problem based on the objective function and the node pressure constraint, the water level constraint and the equipment operation constraint.
3. The method of claim 2, wherein the sequence of discrete operating instructions for the water pump includes a start-stop state of the first water pump and an operating frequency range of the second water pump.
4. A method according to claim 3, wherein the building an objective function based on the economic running cost, the pressure stability penalty and the retention penalty satisfies the following formula: wherein F is the target function, In order to be an economical running cost function, Is in a start-stop state of the ith first water pump in a period t, , For the operation frequency gear of the j-th second water pump in the period t, , In order to adjust the maximum gear position of the bicycle, For the water source level during period t, For instantaneous power consumption calculated from the pump performance curve and the tank water level, For the electricity price of the period t, As a function of the pressure stability penalty, As a result of the desired pressure value, For the pressure of the nth node during period t, In order to retain the penalty function, In order to set the minimum flow rate, For the flow rate of the p-th node in period t, In order to be of economical weight, In order to stabilize the weight of the weight, Is a risk weight.
5. A method according to claim 3, wherein setting node pressure constraints, water level constraints, plant operation constraints of the water supply network dataset comprises: Setting the node pressure to be maintained between a preset minimum service pressure and a preset maximum safety pressure; setting the water level of the water source to be between the safe lower limit water level and the safe upper limit water level of the water source in a dispatching period; And limiting the maximum start and stop times of the first water pump in the continuous scheduling period and the maximum frequency gear change step length allowed between adjacent periods of the second water pump.
6. The method of claim 1, wherein said solving the scheduling optimization problem using branch-and-bound method to generate a sequence of scheduling instructions comprises: Establishing the scheduling optimization problem as a root node; Performing iterative search of branches, delimitations and pruning based on the root node, wherein the branches are used for selecting an undetermined decision variable in a current node to take values to generate a plurality of sub-nodes, the delimitations are used for calculating the lower bound of an objective function value corresponding to each sub-node, and the pruning is used for pruning a sub-node if the lower bound of the sub-node is not lower than the objective function value of the currently obtained optimal feasible solution; and when the iteration termination condition is met, outputting a discrete operation instruction sequence of the water pump corresponding to the current optimal feasible solution as the scheduling instruction sequence.
7. The method of claim 6, wherein establishing the scheduling optimization problem as a root node comprises: obtaining an initial feasible solution, and setting an objective function value of the initial feasible solution as a current optimal objective function value; Performing linear relaxation on discrete decision variables in the scheduling optimization problem to form a continuous relaxation problem; and solving the continuous relaxation problem, and taking the objective function value of the obtained solution as the lower bound of the root node.
8. The method of claim 6, wherein selecting an undetermined decision variable in the current node for value comprises selecting a discrete sequence of operating instructions that is earliest in time sequence or most influential on hydraulic balance as the branch variable using a widest search strategy.
9. The method of claim 6, wherein the iteration termination condition comprises: all nodes are pruned or processed; the difference between the currently obtained objective function value of the optimal feasible solution and the minimum lower bound of all the active nodes is smaller than a preset threshold value; the calculation time of the iterative search reaches the preset duration.
10. A multi-source perceived water supply network dynamic scheduling device is characterized by comprising a communication unit and a processing unit; The communication unit is used for acquiring a water supply network data set, wherein the water supply network data set comprises the pressure, the flow rate, the water source water level and the electricity price of the nodes; The processing unit is used for constructing a scheduling optimization problem based on the water supply pipe network data set, wherein the scheduling optimization problem is a mixed integer programming problem of a discrete operation instruction sequence of the water pump in each period of demodulation period, and a branch delimitation method is adopted to solve the scheduling optimization problem to generate a scheduling instruction sequence.

Description

Multi-source-aware intelligent dynamic scheduling method and device for water supply network Technical Field The application relates to the technical field of water supply networks, in particular to a multi-source-aware water supply network dynamic scheduling method and device. Background The method is characterized in that the water supply safety and stability are guaranteed, the economic operation cost is reduced, the water supply network operation management core target is guaranteed, the current water supply network scheduling is based on manual experience or a simple parameter threshold triggering mechanism, a water pump start-stop and operation frequency adjusting scheme is usually formulated only for local data such as single water source water level, node pressure and the like, multi-source sensing information such as node flow rate, time period electricity price and the like is not fully integrated, the rough scheduling mode is single in optimization target, economic operation cost control, water supply pressure stability guarantee and water flow retention risk avoidance are difficult to achieve, mathematical optimization model support of a system is lacked, scientificity is lacked in scheduling instruction formulation, and problems such as overhigh operation cost, overlarge node pressure fluctuation or partial pipeline water flow retention are easy to occur. Therefore, the problem that the scheduling decision is inaccurate due to the fact that the water supply network scheduling lacks comprehensive utilization of multi-source key data in the prior art. Disclosure of Invention The application provides an intelligent dynamic scheduling method and device for a multi-source-aware water supply network, which solve the problem that scheduling decisions are inaccurate due to the fact that water supply network scheduling is lack of comprehensive utilization of multi-source key data in the prior art. In order to achieve the above purpose, the application adopts the following technical scheme: The method comprises the steps of obtaining a water supply network data set, constructing a scheduling optimization problem based on the water supply network data set, wherein the scheduling optimization problem is a mixed integer programming problem of discrete operation instruction sequences of a water pump in each period of a demodulation period, and solving the scheduling optimization problem by adopting a branch delimitation method to generate a scheduling instruction sequence. Based on the technical scheme, in the multi-source-aware water supply network dynamic scheduling method provided by the application, the node pressure, the flow rate, the water source water level and the electricity price multi-source-aware data are fully integrated, the mixed integer programming scheduling optimization problem is constructed, and the branch delimitation method is adopted for accurately solving, so that a water pump operation instruction sequence adapting to each period in a scheduling period can be generated, and the accuracy of the scheduling decision of the water supply network is obviously improved. With reference to the first aspect, in one possible implementation manner, the scheduling optimization problem is constructed based on the water supply pipe network data set, and the method comprises the steps of setting a discrete operation instruction sequence of the water pump as a decision variable, constructing an objective function based on economic operation cost, pressure stability penalty and retention penalty, setting node pressure constraint, water level constraint and equipment operation constraint of the water supply pipe network data set, and constructing the scheduling optimization problem based on the objective function and the node pressure constraint, the water level constraint and the equipment operation constraint. With reference to the first aspect, in one possible implementation manner, the discrete operation instruction sequence of the water pump includes a start-stop state of the first water pump and an operation frequency gear of the second water pump. With reference to the first aspect, in one possible implementation manner, the objective function is constructed based on the economic operation cost, the pressure stability penalty and the retention penalty to satisfy the following formula: wherein F is an objective function, In order to be an economical running cost function,Is in a start-stop state of the ith first water pump in a period t,,For the operation frequency gear of the j-th second water pump in the period t,,In order to adjust the maximum gear position of the bicycle,For the water source level during period t,For instantaneous power consumption calculated from the pump performance curve and the tank water level,For the electricity price of the period t,As a function of the pressure stability penalty,As a result of the desired pressure value,For the pressure of the nth node during period