Rural drinking water multi-source multi-dimensional dynamic configuration method

Abstract

The invention discloses a multi-water-source multi-dimensional dynamic configuration method for rural drinking water, and belongs to the field of multi-water-source configuration. The method comprises the following steps: collecting water source distribution information and village distribution information of a research area; determining the maximum coverage area of water supply of each water source based on the water source distribution information; according to the village distribution information and the maximum coverage area of water supply of each water source, determining a water demand model of each village for describing the water obtaining working condition of the village based on the water demand of each village; and according to the maximum water supply coverage area of each water source and the water demand model of each village, solving a water supply strategy of each water source to the village. The problem that the construction cost and the water supply efficiency are not considered from the water supply end and the water demand end in an existing method is solved.

Description

Technical Field

[0001] The present invention belongs to the field of multi-source water allocation, and particularly relates to a multi-source multi-dimensional dynamic water allocation method for rural drinking water. Background Art

[0002] With the development of the rural economy and the improvement of living standards, the demand for domestic water by rural residents is increasing continuously. They not only require sufficient water volume but also have higher requirements for water quality.

[0003] The safety of rural drinking water is related to the physical health and quality of life of the vast number of rural residents. In rural areas, problems such as uneven distribution of water resources, diverse water use demands, and water quality changes are prominent. The single-source water supply mode is difficult to meet the growing and complex water use demands, and multi-source dynamic allocation has become an important way to ensure the safety of rural drinking water.

[0004] Overall consideration of water resources at the macro level can better coordinate domestic, production, and ecological water use, realize the sustainable utilization of water resources; is conducive to giving full play to the comprehensive benefits of water conservancy projects and improving the regional water resources allocation ability; and is of great significance for ensuring the water supply safety of large rural areas or ecologically sensitive areas. Summary of the Invention

[0005] Aiming at the above deficiencies in the prior art, the multi-source multi-dimensional dynamic water allocation method for rural drinking water provided by the present invention solves the problem that the existing methods do not consider the construction cost and water supply efficiency from both the water supply end and the water demand end.

[0006] In order to achieve the above invention purpose, the technical solution adopted by the present invention is: a multi-source multi-dimensional dynamic water allocation method for rural drinking water, including:

[0007] Collect the water source distribution information and village distribution information of the research area;

[0008] Based on the water source distribution information, determine the maximum coverage area of each water source for water supply;

[0009] According to the village distribution information and the maximum coverage area of each water source for water supply, based on the water demand of each village, determine the water demand model for each village to describe the water acquisition condition of the village;

[0010] According to the maximum coverage area of each water source for water supply and the water demand model of each village, solve the water supply strategy of each water source to the village.

[0011] Further, the step of determining the water demand model for each village to describe the water acquisition condition of the village according to the village distribution information and the maximum coverage area of each water source for water supply, based on the water demand of each village, specifically is:

[0012] Collect the historical water supply data of each water source and determine the historical water supply sources of each village;

[0013] Obtain the water demand of each village;

[0014] According to the maximum coverage area of each water source's water supply, the historical water supply sources of each village, and the water demand of each village, obtain a water demand model for describing the water acquisition condition of the village.

[0015] Furthermore, the expression of the water demand model is:

[0016]

[0017] where S i is the water demand model of the i-th village; M i is the set of historical water supply sources of the i-th village; is the set of alternative water sources of the i-th village; C i is the water demand of the i-th village; is a binary function used to determine whether to adopt an alternative water source. When is 0, it is set to 0, indicating that there is no need to adopt the alternative water source. Otherwise, it is set to 1, indicating that the alternative water source needs to be adopted; E i is the set of all water sources covering the i-th village; is the total water supply of the water sources in the set of historical water supply sources; C m is the water supply of the m-th historical water supply source in M i ; |M i | is the number of historical water supply sources in M i .

[0018] Furthermore, based on the maximum coverage area of each water source's water supply and the water demand model of each village, solve the water supply strategy of each water source to the village, specifically:

[0019] According to the maximum coverage area of each water source's water supply, divide the research area into multi-source water supply areas and single-source water supply areas;

[0020] Based on the water demand model of the villages in the single-source water supply area, determine the remaining water supply of the water supply source in the single-source water supply area;

[0021] Based on the remaining water supply of the water supply source in the single-source water supply area, determine the water supply of each water supply source in the multi-source water supply area;

[0022] Based on the water supply of each water supply source in the multi-source water supply area and the water demand model of each village in the multi-source water supply area, solve the water supply strategy of each water source to the village.

[0023] Furthermore, based on the water supply of each water supply source in the multi-source water supply area and the water demand model of each village in the multi-source water supply area, solve the water supply strategy of each water source to the village, specifically:

[0024] According to the water supply amounts of each water supply source in the multi-source water supply area and the water demand models of each village in the multi-source water supply area, each water supply source in the multi-source water supply area is used as an agent, and the state space, action space, and reward are defined respectively. The water supply strategy of each water source to the village is solved by using the deep reinforcement learning network model.

[0025] Furthermore, the expression of the state space is:

[0026] s t ={M t ,S t}

[0027] where s t is the state space at time t; M t is the remaining water supply amount of each water supply source in the multi-source water supply area at time t; S t is the water demand model of the multi-source water supply area at time t.

[0028] Furthermore, the expression of the action space is:

[0029] a t ={X(B:S B )}

[0030]

[0031] where a t is the action space at time t; X(B:S B ) is the water supply village selection plan of the water supply sources with non-zero remaining water supply amounts in the multi-source water supply area at time t; B is the set of water supply sources with non-zero remaining water supply amounts in the multi-source water supply area at time t; S B is the set of villages where each water supply source in B is the historical water supply source; is the water supply village action plan of the z-th water supply source with non-zero remaining water supply amounts in the multi-source water supply area at time t; B z is the z-th water supply source with non-zero remaining water supply amounts in the multi-source water supply area at time t; is B z a set of villages where it is the historical water supply source; f(S i (B z,t-1 )) is a binary function for judging whether the village supplied water by B z satisfies the water demand at the previous moment. If so, it is 1, indicating that B z needs to select the next village for water supply. Otherwise, it is 0, indicating that the action of B z remains unchanged and continues to supply water to the village that was supplied water at the previous moment.

[0032] Furthermore, the expression of the reward is:

[0033] r t = α(1 - MAN(f1)) + β(1 - MAN(f2))

[0034]

[0035] where r t is the reward at time t; α is the weight of f1; MAN() is the normalization function; f1 is the first target; β is the weight of f2; f2 is the second target; D j is the number of water supply sources in the j-th village in the multi-source water supply area at time t; is the average number of water supply sources in each village where the number of water supply sources in the multi-source water supply area is not zero at time t; K p is the number of villages supplied by the p-th water supply source in the multi-source water supply area at time t; is the average number of villages supplied with water by water supply sources where the number of villages supplied with water in the multi-source water supply area is not zero at time t.

[0036] The beneficial effects of the present invention are as follows: The present invention fully considers the situation of insufficient water supply sources in rural areas, takes the single-source water supply area into account in the overall water source allocation in rural areas. At the same time, in addition to this, for the multi-source water supply area, using a deep reinforcement learning network model, starting from both the water supply sources and the water demand villages, two targets are constructed. The first target and the second target jointly ensure the utilization rate of water sources and the stability of the water supply end of water demand villages, and a reward function of the deep reinforcement learning network model is constructed based on the first target and the second target to guide the policy solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0038] The following describes the specific embodiments of the present invention to facilitate those skilled in the art of the present technology to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art of the present technology, as long as various changes are within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions made using the concept of the present invention are within the scope of protection.

[0039] As Figure 1 shown, in an embodiment of the present invention, a multi-source multi-dimensional dynamic configuration method for rural drinking water includes:

[0040] Collect the water source distribution information and village distribution information of the research area;

[0041] Based on the water source distribution information, determine the maximum coverage area supplied by each water source;

[0042] Based on the village distribution information and the maximum coverage area of each water source, a water demand model is determined for each village to describe the water supply conditions of the village.

[0043] Based on the maximum coverage area of each water source and the water demand model of each village, the water supply strategy of each water source to the village is solved.

[0044] In this embodiment, taking into account the actual terrain factors, the area that each water supply source can cover is limited. Before configuring the water supply strategy for each village (water demand point), it is necessary to first investigate the maximum coverage range of each water supply source in order to maximize the utilization rate of the water supply source.

[0045] According to the village distribution information and the maximum coverage area of each water source, the water demand model for each village used to describe the water supply conditions of the village is determined based on the water demand of each village. Specifically, it is:

[0046] Collect historical data on water supply from various water sources and determine the historical water supply sources for each village;

[0047] Obtain water demand of each village;

[0048] Based on the maximum coverage area of each water source, the historical water supply sources of each village and the water demand of each village, a water demand model was obtained to describe the water supply conditions of the villages.

[0049] The expression of the water demand model is:

[0050]

[0051] Among them, S i is the water demand model of the i-th village; M i is the historical water supply source set for the i-th village; is the set of alternative water sources for the i-th village; C i is the water demand of the i-th village; is a binary function used to determine whether to use alternative water sources. When it is 0, it is set to 0, indicating that the alternative water source does not need to be used; otherwise, it is set to 1, indicating that the alternative water source needs to be used; E i is the set of all water sources covering the i-th village; is the total water supply of the historical water supply source set; C m M i The water supply of the mth historical water supply source in |M i |For M i The number of historical water supply sources in the country.

[0052] In this embodiment, the initially constructed water demand model is used to describe the historical water acquisition conditions of each village (water demand point). However, when solving the water supply source formula strategy, the water demand model is used to reflect environmental changes.

[0053] Solving the water supply strategy of each water source to the villages according to the maximum coverage area of each water source's water supply and the water demand models of each village specifically includes:

[0054] Dividing the research area into multi-source water supply areas and single-source water supply areas according to the maximum coverage area of each water source's water supply;

[0055] Determining the remaining water supply of the water supply source in the single-source water supply area according to the water demand models of the villages in the single-source water supply area;

[0056] Determining the water supply of each water supply source in the multi-source water supply area according to the remaining water supply of the water supply source in the single-source water supply area;

[0057] Solving the water supply strategy of each water source to the villages according to the water supply of each water supply source in the multi-source water supply area and the water demand models of each village in the multi-source water supply area.

[0058] In this embodiment, the water supply source in the single-source water supply area gives priority to supplying water to the single-source water supply area, and the water demand model of the villages in the single-source water supply area can reflect whether the water supply resources in this area are sufficient. When the water demand model of the villages in the single-source water supply area is an empty set and is 1, it reflects that a new water supply project needs to be built in this area.

[0059] Solving the water supply strategy of each water source to the villages according to the water supply of each water supply source in the multi-source water supply area and the water demand models of each village in the multi-source water supply area specifically includes:

[0060] Regarding each water supply source in the multi-source water supply area as an agent according to the water supply of each water supply source in the multi-source water supply area and the water demand models of each village in the multi-source water supply area, respectively defining the state space, action space and reward, and using the deep reinforcement learning network model to solve the water supply strategy of each water source to the villages.

[0061] In this embodiment, the solution of the water supply strategy of the water source to each village is converted into a Markov decision process and solved using the deep reinforcement learning network model.

[0062] The expression of the state space is:

[0063] s t ={M t ,S t}

[0064] where st is the state space at time t; M t is the remaining water supply of each water supply source in the multi-source water supply area at time t; S t is the water demand model of the multi-source water supply area at time t.

[0065] In this embodiment, two states need to be monitored in real time. One is the remaining water supply of each water supply source, and the other is the water acquisition situation at the water demand points. In this embodiment, the water supply mentioned is in units of days, including the maximum daily water supply, the remaining daily water supply, etc.

[0066] The expression of the action space is:

[0067] a t ={X(B:S B )}

[0068]

[0069] where a t is the action space at time t; X(B:S B ) is the water supply village selection plan for water supply sources with non-zero remaining water supply in the multi-source water supply area at time t; B is the set of water supply sources with non-zero remaining water supply in the multi-source water supply area at time t; S B is the set of villages where each water supply source in B is the historical water supply source; is the water supply village action plan for the z-th water supply source with non-zero remaining water supply in the multi-source water supply area at time t; B z is the z-th water supply source with non-zero remaining water supply in the multi-source water supply area at time t; is B z is the set of villages where it is the historical water supply source; f(S i (B z,t-1 )) is a binary function for judging whether the villages supplied with water at the previous moment meet the water demand. If so, it is 1, indicating that B z needs to select the next village for water supply. Otherwise, it is 0, indicating that the action of B z remains unchanged and continues to supply water to the village supplied with water at the previous moment. z

[0070] In this embodiment, the selection of actions follows the water supply stability and avoids unnecessary facility construction. When the current water supply source supplies water to the corresponding village, if the current water supply source still has remaining water supply and the water demand of the corresponding village is not met, the current water supply source should maintain the current action.

[0071] The expression of the reward is:

[0072] r t= α(1 - MAN(f1)) + β(1 - MAN(f2))

[0073]

[0074] where r t is the reward at time t; α is the weight of f1; MAN() is the normalization function; f1 is the first target; β is the weight of f2; f2 is the second target; D j is the number of water supply sources in the j-th village in the multi-source water supply area at time t; is the average number of water supply sources in each village where the number of water supply sources in the multi-source water supply area is not 0 at time t; K p is the number of villages supplied by the p-th water supply source in the multi-source water supply area at time t; is the average number of villages supplied by water supply sources where the number of villages supplied by water supply sources in the multi-source water supply area is not 0 at time t.

[0075] In this embodiment, the first target and the second target respectively ensure the stability of the water supply sources in each village and the maximum utilization rate of each water source.

[0076] In this embodiment, the finally solved strategy is not the water supply order, but which villages each water supply source supplies water to and how much water is supplied per day.

[0077] For different seasonal water demands, different water supply strategies can be solved.

[0078] Similarly, the water demand models of each village at the moment when the deep reinforcement learning network model is solved can also reflect whether there is a lack of water supply projects in the corresponding area.

Claims

1. A multi-source multi-dimensional dynamic configuration method for rural drinking water, characterized in that Including: Collect the water source distribution information and village distribution information of the research area; Based on the water source distribution information, determine the maximum coverage area of each water source's water supply; According to the village distribution information and the maximum coverage area of each water source's water supply, determine the water demand model for each village to describe the water acquisition condition of the village based on the water demand of each village; According to the maximum coverage area of each water source's water supply and the water demand model of each village, solve the water supply strategy of each water source to the village.

2. The multi-source multi-dimensional dynamic configuration method for rural drinking water according to claim 1, wherein The step of determining the water demand model for each village to describe the water acquisition condition of the village based on the water demand of each village according to the village distribution information and the maximum coverage area of each water source's water supply is specifically as follows: Collect the historical water supply data of each water source and determine the historical water supply sources of each village; Obtain the water demand of each village; According to the maximum coverage area of each water source's water supply, the historical water supply sources of each village, and the water demand of each village, obtain the water demand model for describing the water acquisition condition of the village.

3. The multi-source multi-dimensional dynamic configuration method for rural drinking water according to claim 2, wherein The expression of the water demand model is: Among them, S i is the water demand model of the i-th village; M i is the set of historical water supply sources of the i-th village; is the set of alternative water sources of the i-th village; C i is the water demand of the i-th village; is a binary function used to judge whether to adopt alternative water sources. When is 0, it is set to 0, indicating that there is no need to adopt alternative water sources; otherwise, it is set to 1, indicating that alternative water sources need to be adopted; E i is the set of all water sources covering the i-th village; is the total water supply of the water sources in the set of historical water supply sources; C m is the water supply of the m-th historical water supply source in M i ; |M i | is the number of historical water supply sources in M i .

4. The rural drinking water multi-source multi-dimensional dynamic configuration method according to claim 1, characterized in that The step of solving the water supply strategy of each water source to the village according to the maximum coverage area of each water source's water supply and the water demand model of each village is specifically as follows: According to the maximum coverage area of each water source's water supply, divide the research area into multi-source water supply areas and single-source water supply areas; According to the water demand model of the villages in the single-source water supply area, determine the remaining water supply of the water supply source in the single-source water supply area; According to the remaining water supply of the water supply source in the single-source water supply area, determine the water supply of each water supply source in the multi-source water supply area; According to the water supply of each water supply source in the multi-source water supply area and the water demand model of the villages in the multi-source water supply area, solve the water supply strategy of each water source to the village.

5. The multi-source multi-dimensional dynamic configuration method for rural drinking water according to claim 1, characterized in that The step of solving the water supply strategy of each water source to the village according to the water supply of each water supply source in the multi-source water supply area and the water demand model of the villages in the multi-source water supply area is specifically as follows: According to the water supply of each water supply source in the multi-source water supply area and the water demand model of the villages in the multi-source water supply area, take each water supply source in the multi-source water supply area as an agent, and respectively define the state space, action space, and reward, and use the deep reinforcement learning network model to solve the water supply strategy of each water source to the village.

6. The rural drinking water multi-source multi-dimensional dynamic configuration method according to claim 5, wherein, The expression of the state space is: s t = {M t , S t} Among them, s t is the state space at time t; M t is the remaining water supply of each water supply source in the multi-source water supply area at time t; S t is the water demand model of the multi-source water supply area at time t.

7. The method for multi-source multi-dimensional dynamic configuration of rural drinking water according to claim 5, wherein The expression of the action space is: a t ={X(B:S B )} Among them, a t is the action space at time t; X(B:S B ) is the water supply village selection scheme for the water supply source with non-zero remaining water supply in the multi-source water supply area at time t; B is the set of water supply sources with non-zero remaining water supply in the multi-source water supply area at time t; S B The set of villages for which each water source in B is the historical water supply source; B is the action plan for the water supply village of the zth water supply source in the multi-source water supply area whose remaining water supply is not 0 at time t; z The zth water source whose remaining water supply in the multi-source water supply area is not 0 at time t; For B z A collection of villages that are historical water sources; f(S i (B z,t-1 )) is used to judge B z The binary function of whether the village supplied with water at the last moment meets the water demand. If so, it is 1, indicating that B z The next village needs to be selected for water supply, otherwise, it is 0, indicating B z The action remains unchanged and water supply continues to be provided to the village that was supplied with water at the last moment.

8. The multi-source multi-dimensional dynamic configuration method for rural drinking water according to claim 5, wherein The expression of the reward is: r t = α(1 - MAN(f1)) + β(1 - MAN(f2)) Among them, r t is the reward at time t; α is the weight of f1; MAN() is the normalization function; f1 is the first target; β is the weight of f2; f2 is the second target; D j is the number of water supply sources in the j-th village in the multi-source water supply area at time t; is the average number of water supply sources in each village where the number of water supply sources in the multi-source water supply area is not zero at time t; K p is the number of villages supplied by the p-th water supply source in the multi-source water supply area at time t; is the average number of villages supplied by water supply sources where the number of villages supplied by water supply sources in the multi-source water supply area is not zero at time t.

Images