Cross-basin multi-station hydropower station centralized control optimization platform

Abstract

The invention relates to the technical field of hydropower station water resource dispatching management, in particular to a centralized control optimization platform for a cross-basin multi-station hydropower station. The method comprises the following steps: a data acquisition unit acquires hydrological data, power grid load data and environmental meteorological data by using a variable acquisition frequency mechanism; the hydrologic monitoring unit analyzes and monitors the cross-basin hydrologic dynamic state in real time based on the hydrologic data, and predicts the cross-basin hydrologic change by using a hydrologic prediction model; the hydrological scheduling simulation unit predicts an interbasin hydrological change result based on a hydrological prediction model to simulate hydrological scheduling, and constructs a scheduling strategy; the water resource scheduling unit constructs a self-adaptive global optimization scheduling framework and generates an optimal scheduling strategy; and the emergency dispatching unit is used for handling water resource dispatching under emergency conditions. According to the centralized control optimization platform for the cross-basin multi-station hydropower station, the scheduling strategy of the hydropower station is dynamically adjusted in real time through the self-adaptive global optimization scheduling framework in combination with the hydrological prediction model, and stable operation of cross-basin water resources is subjected to centralized control optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of water resource dispatching and management of hydropower stations, and in particular to a centralized control optimization platform for multi-station hydropower stations across river basins. Background Art

[0002] A cross-basin multi-station hydropower station centralized control optimization platform aims to achieve efficient utilization of water resources and optimization of power generation efficiency. Through an adaptive global optimization scheduling framework combined with a hydrological prediction model, it controls the water resource scheduling and power generation strategies of multiple hydropower stations across river basins, and achieves a reasonable allocation of water resources and a dynamic balance between power generation plans and actual water demand.

[0003] The existing cross-basin multi-station hydropower station centralized control optimization platform is usually difficult to dynamically adjust the water resources scheduling strategy in real time to cope with complex hydrological changes and meteorological conditions. In addition, due to the large fluctuations in water resources and the high difficulty in coordinating cross-basin hydropower stations, it will lead to waste of water resources and fail to effectively deal with the water level imbalance caused by extreme weather. Therefore, a cross-basin multi-station hydropower station centralized control optimization platform is designed. Summary of the invention

[0004] The purpose of the present invention is to provide a cross-basin multi-station hydropower station centralized control optimization platform to solve the problems raised in the above background technology, namely, large fluctuations in water resources and high difficulty in coordinating cross-basin hydropower stations, which will lead to waste of water resources and inability to effectively cope with water level imbalance caused by extreme weather.

[0005] To achieve the above object, the present invention provides a cross-basin multi-station hydropower station centralized control optimization platform, comprising:

[0006] A data acquisition unit, wherein the data acquisition unit uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system;

[0007] It also includes a hydrological monitoring unit, which monitors the cross-basin hydrological dynamics based on real-time analysis of hydrological data, and predicts cross-basin hydrological changes using a hydrological prediction model in combination with historical hydrological data;

[0008] It also includes a hydrological dispatch simulation unit, which simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station;

[0009] It also includes a water resource scheduling unit, which constructs an adaptive global optimization scheduling framework, and dynamically adjusts the scheduling strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal scheduling strategy for each hydropower station;

[0010] It also includes an emergency dispatching unit, which is used to handle water resource dispatching in emergencies and emergency situations.

[0011] As a further improvement of the technical solution, the data acquisition unit deploys sensors in hydropower stations and rivers, builds an Internet of Things sensor network, and uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system in real time;

[0012] The variable acquisition frequency mechanism is a mechanism for dynamically adjusting the data acquisition frequency according to the needs of the hydropower station and environmental conditions;

[0013] Among them, the hydrological data includes river water level, flow rate, flow and precipitation, and is stored in the edge node server through 5G transmission technology; the power grid load data includes power demand and load changes in each time period, and is transmitted to the central server through 5G transmission technology; the environmental meteorological data includes the meteorological temperature, humidity and rainfall of each power station, and is transmitted to the central server through 5G transmission technology.

[0014] As a further improvement of the technical solution, the hydrological monitoring unit includes a hydrological dynamic analysis module and a hydrological change prediction module;

[0015] Wherein, the hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data;

[0016] The hydrological change prediction module predicts cross-basin hydrological changes using a hydrological prediction model based on hydrological dynamics combined with historical hydrological data.

[0017] As a further improvement of the technical solution, the hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data. The specific steps are as follows:

[0018] S2.1.1. Obtain real-time hydrological data from the data acquisition unit, including river water level h(t), flow velocity v(t), flow Q(t) and precipitation P(t);

[0019] S2.1.2. Calculate the water inflow and outflow of the hydropower station as follows:

[0020] Q in (t) = v in (t) × A;

[0021] Q out (t) = v out (t) × A;

[0022] Among them, Q in (t) is the water inflow of the hydropower station at time t; Q out(t) is the water outflow of the hydropower station at time t; A is the cross-sectional area of ​​the waterway of the hydropower station; v in (t) is the water resource inlet flow rate of the hydropower station at time t; v out (t) is the outlet flow rate of water resources of the hydropower station at time t;

[0023] S2.1.3. Calculate the dynamic change of water level in the hydropower station based on the water level change formula, as follows:

[0024]

[0025] Among them, Δh(t) represents the change of reservoir water level at time t;

[0026] S2.1.4. Real-time monitoring of water volume changes in the basin through the flow conservation equation, as follows:

[0027]

[0028] S2.1.5. Set the warning threshold θ of the water level change rate h , if the water level change rate exceeds the warning threshold θ h The alarm is triggered immediately and fed back to the emergency dispatch unit for emergency processing.

[0029] As a further improvement of the technical solution, the hydrological change prediction module uses a hydrological prediction model to predict cross-basin hydrological changes based on hydrological dynamics combined with historical hydrological data. The specific steps are as follows:

[0030] S2.2.1. Obtain historical hydrological data X from the data acquisition unit (1) hist ={h(t-1),v(t-1),Q(t-1),P(t-1),…,h(tn),v(tn),Q(tn),P(tn)}, and combined with real-time hydrological data as the input data set X of the hydrological prediction model t ={h(t),v(t),Q(t),P(t),h(t-1),v(t-1),Q(t-1),P(t-1),…};

[0031] Among them, h(t-1) is the water level of the hydropower station at time t-1; v(t-1) is the water resource flow rate of the hydropower station at time t-1; Q(t-1) is the water resource flow rate of the hydropower station at time t-1; P(t-1) is the precipitation of the hydropower station at time t-1; h(tn) is the water level of the hydropower station at time tn; v(tn) is the water resource flow rate of the hydropower station at time tn; Q(tn) is the water resource flow rate of the hydropower station at time tn; P(tn) is the precipitation of the hydropower station at time tn;

[0032] S2.2.2. Obtain meteorological data Y from the meteorological forecast systemt = {P forecast (t),T(t),RH(t)}, and with the dataset X t Combined with the complete input data set {X t ,Y t};

[0033] S2.2.3. Use long short-term memory network to build a hydrological prediction model.

[0034] As a further improvement of this technical solution, the S2.2.3, using a long short-term memory network to construct a hydrological prediction model, is as follows:

[0035] Input layer: The input is a dataset {X t ,Y t};

[0036] Hidden Layer:

[0037] i t =σ(W i ·[h t-1 ,X t ]+b i );

[0038] f t =σ(W f ·[h t-1 ,X t ]+b f );

[0039] o t =σ(W o ·[h t-1 ,X t ]+b o );

[0040] Among them, W i is the input gate weight matrix; W f is the forget gate weight matrix; W o is the output gate weight matrix; b i is the input gate bias term; b f is the forget gate bias term; b o is the output gate bias term; h t-1 is the hidden layer output at time t-1; σ is the activation function;

[0041] Memory unit update:

[0042]

[0043] in, is the candidate memory unit state; tanh(·) is the hyperbolic tangent function; Wc To convert the hidden state h of the previous time step t-1 and X t Mapping to candidate memory states The weight matrix of c is the bias term; C t is the state of the memory unit at the current time t; f t is the output value of the forget gate; i t is the output value of the input gate;

[0044] Final output:

[0045] h t =o t *tanh(C t );

[0046] Among them, h t is the hidden layer output at time t; o t is the output gate activation value at time t;

[0047] Output layer:

[0048]

[0049] in, is the hydrological data predicted at time t+1; W o is the weight matrix of the output layer; h t is the hidden layer output at time t.

[0050] As a further improvement of the technical solution, the hydrological dispatch simulation unit simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station. The specific steps are as follows:

[0051] S3.1. Predicted cross-basin hydrological changes Calculate the total amount of available water resources W in the basin at time t+1 total (t+1), as follows:

[0052]

[0053] in, is the predicted inflow at time t; Predicted precipitation at time t; Predict the flow rate at time t;

[0054] S3.2. Calculate the water volume W required by the i-th hydropower station at time t+1 based on the power generation demand and historical water use data of each hydropower station. demand (i,t+1), as follows

[0055]

[0056] Among them, P gen (i, t+1) is the power generation of the ith hydropower station at time t+1; η is the power generation efficiency of the ith hydropower station; ρ is the density of water; g is the acceleration of gravity; is the water level of the i-th hydropower station at time t+1;

[0057] S3.3, according to the water volume W required by the i-th hydropower station at time t+1 demand (i, t+1) and the total amount of available water resources in the basin at time t+1 W total (t+1), preliminary allocation of water resources is as follows:

[0058]

[0059] Among them, W alloc (i,t+1) is the water resource allocation of the i-th hydropower station at time t+1; μ i is the priority weight of the ith hydropower station; N is the total number of hydropower stations in the basin;

[0060] S3.4. According to the water resources allocation results W alloc (i, t+1) and the current water storage capacity of the hydropower station H(i, t), simulate the water release strategy and water storage strategy, and form a scheduling strategy, which is as follows:

[0061] Water release strategy:

[0062] Q out (i,t+1)=W alloc (i,t+1) / Δt;

[0063] Among them, Q out (i, t+1) is the water release strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step;

[0064] Water storage strategy:

[0065] H(i,t+1)=H(i,t)+W alloc (i,t+1)-Q out (i,t+1);

[0066] Among them, H(i,t+1) is the water storage strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step.

[0067] As a further improvement of the technical solution, the water resource scheduling unit constructs an adaptive global optimization scheduling framework, and dynamically adjusts the scheduling strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal scheduling strategy for each hydropower station. The specific steps are as follows:

[0068] S4.1. Establish global optimization scheduling objective function F:

[0069] S4.2. Calculate and predict the change in water resources W at time t+1 based on future environmental meteorological data forecast (t+1):

[0070] W forecast (t+1)=f(P forecast (t+1),T(t+1),RH(t+1));

[0071] Among them, P forecast (t+1) is the predicted precipitation at time t+1; T(t+1) is the predicted temperature at time t+1; RH(t+1) is the predicted relative humidity at time t+1;

[0072] S4.3. Based on the predicted water resource change at time t+1, W forecast (t+1), dynamically adjust the water resource allocation W of the i-th hydropower station at time t+1 alloc (i,t+1):

[0073] W alloc (i,t+1)=W alloc (i,t)+W forecast (t+1);

[0074] Among them, W alloc (i,t) is the water resource allocation of the i-th hydropower station at time t;

[0075] S4.4. Optimize water release strategy:

[0076]

[0077] Among them, Q' out (i, t+1) is the optimal water release strategy of the i-th hydropower station at time t+1; Q out (i, t+1) is the original water release strategy of the i-th hydropower station at time t+1;

[0078] S4.5. Optimize water storage strategy:

[0079] H'(i,t+1)=H(i,t+1)+ΔH adjust (i,t+1);

[0080] Among them, H'(i,t+1) is the optimized water storage strategy of the i-th hydropower station at time t+1; H(i,t+1) is the original water storage strategy of the i-th hydropower station at time t+1; ΔH adjust (i, t+1) is the water storage strategy adjustment value of the i-th hydropower station at time t+1;

[0081] ΔH adjust (i,t+1)=k1·ΔW forecast (t+1)+k2·(H max (i)-H(i,t))+k3·P forecast (t+1);

[0082] Among them, H max (i) is the maximum water storage capacity of the reservoir of the i-th hydropower station; k1 is the weight coefficient of the predicted value of water resources change; k2 is the weight coefficient of the reservoir water storage capacity difference; k3 is the weight coefficient of the predicted value of precipitation.

[0083] As a further improvement of the technical solution, the establishment of the global optimization scheduling objective function F is as follows:

[0084]

[0085] Among them, α i is the weight coefficient of the power generation of the i-th hydropower station; P gen (i) is the power generation of the i-th hydropower station; β i is the weight coefficient of water resource allocation error; W alloc (i,t) is the water resource allocation of the i-th hydropower station at time t; W demand (i,t) is the water required by the i-th hydropower station at time t; N is the total number of hydropower stations in the basin;

[0086] Construct water resource balance constraints:

[0087] W alloc (i,t)≤W total (t);

[0088] Among them, W alloc (i,t)≤W total (t) indicates that the water resources allocated to each hydropower station must not exceed the total water resources in the basin.

[0089] As a further improvement of the technical solution, the emergency dispatch unit is used to handle water resource dispatch in emergencies and emergency situations, including an alarm unit and an emergency processing unit;

[0090] The alarm unit monitors the data of the hydrological monitoring unit and the hydrological dispatch simulation unit in real time. If an abnormal parameter is detected that exceeds the safety range, the system will trigger an alarm mechanism;

[0091] The emergency processing unit is used to process water resource scheduling according to emergency situations, as follows:

[0092]

[0093] in, is the emergency water discharge of the i-th hydropower station at time t+1; H safe It is the safety water level threshold of the hydropower station.

[0094] Compared with the prior art, the present invention has the following beneficial effects:

[0095] 1. In this cross-basin multi-station hydropower station centralized control optimization platform, based on the adaptive global optimization scheduling framework combined with real-time hydrological and meteorological data, the water resource allocation and power generation strategies of each hydropower station can be dynamically adjusted to ensure the efficient use of water resources and the stability of power generation.

[0096] 2. In this cross-basin multi-station hydropower station centralized control optimization platform, a hydrological prediction model is constructed to make high-precision predictions of future hydrological changes, so as to predict the trend of water resource changes in advance, optimize the water release and storage strategies of hydropower stations, and avoid scheduling errors and waste of resources caused by climate change or emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 It is the overall flow chart of the present invention;

[0098] The meaning of each number in the figure is:

[0099] 1. Data acquisition unit; 2. Hydrological monitoring unit; 3. Hydrological dispatch simulation unit; 4. Water resources dispatch unit; 5. Emergency dispatch unit. DETAILED DESCRIPTION

[0100] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0101] See also Figure 1 As shown, a cross-basin multi-station hydropower station centralized control optimization platform is provided, including:

[0102] A data acquisition unit 1, wherein the data acquisition unit 1 uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system;

[0103] In this embodiment, the data acquisition unit 1 deploys sensors in hydropower stations and rivers to build an IoT sensor network, and uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system in real time;

[0104] The variable acquisition frequency mechanism is a mechanism for dynamically adjusting the data acquisition frequency according to the needs of the hydropower station and environmental conditions;

[0105] In this embodiment, the variable acquisition frequency mechanism automatically switches the frequency of data acquisition according to the current operating conditions of the hydropower station; the variable acquisition frequency mechanism automatically determines whether the acquisition frequency needs to be increased by real-time monitoring of environmental changes, emergencies and system requirements, as follows:

[0106] When extreme weather conditions are detected, the system will increase the frequency of hydrological data collection to every minute or even every second to track water level changes and flow rates in real time;

[0107] When equipment abnormalities are detected, the frequency of collecting power generation equipment status data will be increased from 5 minutes to every second to ensure accurate monitoring of equipment status and timely response;

[0108] The grid load data will automatically increase the collection frequency during peak hours to ensure accurate real-time monitoring of grid load changes;

[0109] Among them, the hydrological data includes river water level, flow rate, flow and precipitation, and is stored in the edge node server through 5G transmission technology; the power grid load data includes power demand and load changes in each time period, and is transmitted to the central server through 5G transmission technology; the environmental meteorological data includes the meteorological temperature, humidity and rainfall of each power station, and is transmitted to the central server through 5G transmission technology.

[0110] In this embodiment, the IoT sensor network is a network system composed of a large number of distributed sensor devices interconnected through other communication protocols 5G, in which each sensor is responsible for monitoring and collecting data, and transmitting these data in real time to the central processing unit or edge node server for processing and analysis; the purpose of building the IoT sensor network is to monitor, intelligently manage and automatically control the water resources of the hydropower station in real time, and realize automatic regulation and optimization operation.

[0111] It also includes a hydrological monitoring unit 2, which monitors the cross-basin hydrological dynamics based on real-time analysis of hydrological data, and predicts cross-basin hydrological changes using a hydrological prediction model in combination with historical hydrological data;

[0112] In this embodiment, the hydrological monitoring unit 2 includes a hydrological dynamic analysis module and a hydrological change prediction module;

[0113] Wherein, the hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data;

[0114] The hydrological change prediction module predicts cross-basin hydrological changes using a hydrological prediction model based on hydrological dynamics combined with historical hydrological data.

[0115] The hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data. The specific steps are as follows:

[0116] S2.1.1, obtain real-time hydrological data from data acquisition unit 1, including river water level h(t), flow velocity v(t), flow Q(t) and precipitation P(t);

[0117] S2.1.2. Calculate the water inflow and outflow of the hydropower station as follows:

[0118] Q in (t) = v in (t) × A;

[0119] Q out (t) = v out (t) × A;

[0120] Among them, Q in (t) is the water inflow of the hydropower station at time t; Q out (t) is the water outflow of the hydropower station at time t; A is the cross-sectional area of ​​the waterway of the hydropower station; v in (t) is the water resource inlet flow rate of the hydropower station at time t; v out (t) is the outlet flow rate of water resources of the hydropower station at time t;

[0121] S2.1.3. Calculate the dynamic change of water level in the hydropower station based on the water level change formula, as follows:

[0122]

[0123] Among them, Δh(t) represents the change of reservoir water level at time t;

[0124] S2.1.4. Real-time monitoring of water volume changes in the basin through the flow conservation equation, as follows:

[0125]

[0126] S2.1.5. Set the warning threshold θ of the water level change rate h , if the water level change rate exceeds the warning threshold θ h An alarm is triggered immediately and fed back to the emergency dispatch unit 5 for emergency processing.

[0127] In this embodiment, the hydrological change prediction module uses a hydrological prediction model to predict cross-basin hydrological changes based on hydrological dynamics and historical hydrological data. The specific steps are as follows:

[0128] S2.2.1. Obtain historical hydrological data X from data acquisition unit 1 hist = {g(t-1), v(t-1), Q(t-1), P(t-1), …, h(tn), v(tn), Q(tn), P(tn)}, and combined with real-time hydrological data as the input data set X of the hydrological prediction model t ={h(t),v(t),Q(t),P(t),h(t-1),v(t-1),Q(t-1),P(t-1),…};

[0129] Among them, h(t-1) is the water level of the hydropower station at time t-1; v(t-1) is the water resource flow rate of the hydropower station at time t-1; Q(t-1) is the water resource flow rate of the hydropower station at time t-1; P(t-1) is the precipitation of the hydropower station at time t-1; h(tn) is the water level of the hydropower station at time tn; v(tn) is the water resource flow rate of the hydropower station at time tn; Q(tn) is the water resource flow rate of the hydropower station at time tn; P(tn) is the precipitation of the hydropower station at time tn;

[0130] S2.2.2. Obtain meteorological data Y from the meteorological forecast system t = {P forecast (t),T(t),RH(t)}, and with the dataset X t Combined with the complete input data set {X t ,Y t};

[0131] S2.2.3. Use long short-term memory network to build a hydrological prediction model.

[0132] S2.2.3, using long short-term memory network to build a hydrological prediction model, is as follows:

[0133] Input layer: The input is a dataset {X t ,Y t};

[0134] Hidden Layer:

[0135] ut=σ(W i ·[h t-1 ,X t ]+b i );

[0136] f t =σ(W f ·[h t-1 ,X t ]+b f );

[0137] ot =σ(W o ·[h t-1 ,X t ]+b o );

[0138] Among them, W i is the input gate weight matrix; W f is the forget gate weight matrix; W o is the output gate weight matrix; b i is the input gate bias term; b f is the forget gate bias term; b o is the output gate bias term; h t-1 is the hidden layer output at time t-1; σ is the activation function;

[0139] Memory unit update:

[0140]

[0141] in, is the candidate memory unit state; tanh(·) is the hyperbolic tangent function; W c To convert the hidden state h of the previous time step t-1 and X t Mapping to candidate memory states The weight matrix of c is the bias term; C t is the state of the memory unit at the current time t; f t is the output value of the forget gate; i t is the output value of the input gate;

[0142] Final output:

[0143] h t =o t *tanh(C t );

[0144] Among them, h t is the hidden layer output at time t; o t is the output gate activation value at time t;

[0145] Output layer:

[0146]

[0147] in, is the hydrological data predicted at time t+1; W o is the weight matrix of the output layer; h t is the hidden layer output at time t.

[0148] It also includes a hydrological dispatch simulation unit 3, which simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station;

[0149] In this embodiment, the hydrological dispatch simulation unit 3 simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station. The specific steps are as follows:

[0150] S3.1. Predicted cross-basin hydrological changes Calculate the total amount of available water resources W in the basin at time t+1 total (t+1), as follows:

[0151]

[0152] in, is the predicted inflow at time t; Predicted precipitation at time t; Predict the flow rate at time t;

[0153] S3.2. Calculate the water volume W required by the i-th hydropower station at time t+1 based on the power generation demand and historical water use data of each hydropower station. demand (i,t+1), as follows

[0154]

[0155] Among them, P gen (i, t+1) is the power generation of the ith hydropower station at time t+1; η is the power generation efficiency of the ith hydropower station; ρ is the density of water; g is the acceleration of gravity; is the water level of the i-th hydropower station at time t+1;

[0156] S3.3, according to the water volume W required by the i-th hydropower station at time t+1 demand (i, t+1) and the total amount of available water resources in the basin at time t+1 W total (t+1), preliminary allocation of water resources is as follows:

[0157]

[0158] Among them, W alloc (i,t+1) is the water resource allocation of the i-th hydropower station at time t+1; μ i is the priority weight of the ith hydropower station; N is the total number of hydropower stations in the basin;

[0159] S3.4. According to the water resources allocation results W alloc(i, t+1) and the current water storage capacity of the hydropower station H(i, t), simulate the water release strategy and water storage strategy, and form a scheduling strategy, which is as follows:

[0160] Water release strategy:

[0161] Q out (i,t+1)=W alloc (i,t+1) / Δt;

[0162] Among them, Q out (i, t+1) is the water release strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step;

[0163] Water storage strategy:

[0164] H(i,t+1)=H(i,t)+W alloc (i,t+1)-Q out (i,t+1);

[0165] Among them, H(i,t+1) is the water storage strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step.

[0166] It also includes a water resource scheduling unit 4, which constructs an adaptive global optimization scheduling framework, and dynamically adjusts the scheduling strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal scheduling strategy of each hydropower station;

[0167] In this embodiment, the water resource scheduling unit 4 constructs an adaptive global optimization scheduling framework, and dynamically adjusts the scheduling strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal scheduling strategy for each hydropower station. The specific steps are as follows:

[0168] S4.1. Establish global optimization scheduling objective function F:

[0169] S4.2. Calculate and predict the change in water resources W at time t+1 based on future environmental meteorological data forecast (t+1):

[0170] W forecast (t+1)=f(P forecast (t+1),T(t+1),RH(t+1));

[0171] Among them, P forecast (t+1) is the predicted precipitation at time t+1; T(t+1) is the predicted temperature at time t+1; RH(t+1) is the predicted relative humidity at time t+1;

[0172] S4.3. Based on the predicted water resource change at time t+1, W forecast(t+1), dynamically adjust the water resource allocation W of the i-th hydropower station at time t+1 alloc (i,t+1):

[0173] W alloc (i,t+1)=W alloc (i,t)+W forecast (t+1);

[0174] Among them, W alloc (i,t) is the water resource allocation of the i-th hydropower station at time t;

[0175] S4.4. Optimize water release strategy:

[0176]

[0177] Among them, Q' out (i, t+1) is the optimal water release strategy of the i-th hydropower station at time t+1; Q out (i, t+1) is the original water release strategy of the i-th hydropower station at time t+1;

[0178] S4.5. Optimize water storage strategy:

[0179] H'(i,t+1)=H(i,t+1)+ΔH adjust (i,t+1);

[0180] Among them, H'(i,t+1) is the optimized water storage strategy of the i-th hydropower station at time t+1; H(i,t+1) is the original water storage strategy of the i-th hydropower station at time t+1; ΔH adjust (i, t+1) is the water storage strategy adjustment value of the i-th hydropower station at time t+1;

[0181] ΔH adjust (i,t+1)=k1·ΔW forecast (t+1)+k2·(H max (i)-H(i,t))+k3·P forecast (t+1);

[0182] Among them, H max (i) is the maximum water storage capacity of the reservoir of the i-th hydropower station; k1 is the weight coefficient of the predicted value of water resources change; k2 is the weight coefficient of the reservoir water storage capacity difference; k3 is the weight coefficient of the predicted value of precipitation.

[0183] In this embodiment, k1·ΔW forecast(t+1) is the impact of the hydrological prediction model on future water resource changes; if it is predicted that water resources will increase at time t+1 in the future, this term is positive and the water storage capacity should be increased accordingly; if water resources decrease, this term is negative and the water storage capacity should be reduced to release water resources to the downstream;

[0184] k2·(H max (i)-H(i,t)) is the impact of the current reservoir water storage state on water storage adjustment. If the current reservoir water storage H(i,t) is close to the maximum water storage H max (i), then the adjustment value should be reduced to prevent the reservoir from overflowing;

[0185] k3·P forecast (t+1) is the impact of future rainfall forecast on water storage strategy; if a large amount of rainfall is predicted in the future, P forecast (t+1), water storage should be reduced to prevent the reservoir from overflowing.

[0186] In this embodiment, a global optimization scheduling objective function F is established, which is as follows:

[0187]

[0188] Among them, α i is the weight coefficient of the power generation of the i-th hydropower station; P gen (i) is the power generation of the i-th hydropower station; β i is the weight coefficient of water resource allocation error; W alloc (i,t) is the water resource allocation of the i-th hydropower station at time t; W demand (i,t) is the water required by the i-th hydropower station at time t; N is the total number of hydropower stations in the basin;

[0189] Construct water resource balance constraints:

[0190] W alloc (i,t)≤W total (t);

[0191] Among them, W alloc (i,t)≤W total (t) indicates that the water resources allocated to each hydropower station must not exceed the total water resources in the basin.

[0192] It also includes an emergency dispatch unit 5, which is used to handle water resource dispatch in emergencies and emergency situations;

[0193] In this embodiment, the emergency dispatch unit 5 is used to handle water resource dispatch in emergencies and emergency situations, and includes an alarm unit and an emergency processing unit;

[0194] The alarm unit monitors the data of the hydrological monitoring unit 2 and the hydrological dispatch simulation unit 3 in real time. If an abnormal parameter is detected that exceeds the safety range, the system will trigger an alarm mechanism;

[0195] The emergency processing unit is used to process water resource scheduling according to emergency situations, as follows:

[0196]

[0197] in, is the emergency water discharge of the i-th hydropower station at time t+1; H safe It is the safety water level threshold of the hydropower station.

[0198] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A cross-basin multi-station hydropower station centralized control optimization platform, characterized in that: include: A data acquisition unit (1), wherein the data acquisition unit (1) uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system; A hydrological monitoring unit (2), wherein the hydrological monitoring unit (2) monitors cross-basin hydrological dynamics based on real-time analysis of hydrological data, and predicts cross-basin hydrological changes using a hydrological prediction model in combination with historical hydrological data; A hydrological dispatch simulation unit (3), wherein the hydrological dispatch simulation unit (3) simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station; A water resource dispatching unit (4), wherein the water resource dispatching unit (4) constructs an adaptive global optimization dispatching framework, and dynamically adjusts the dispatching strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal dispatching strategy of each hydropower station; An emergency dispatch unit (5), the emergency dispatch unit (5) is used to handle water resource dispatch in emergencies and emergency situations.

2. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 1 is characterized by: The data acquisition unit (1) deploys sensors in the hydropower station and the river to build an Internet of Things sensor network, and uses a variable acquisition frequency mechanism to collect hydrological data, power grid load data, and environmental meteorological data in the hydropower station system in real time; The variable acquisition frequency mechanism is a mechanism for dynamically adjusting the data acquisition frequency according to the needs of the hydropower station and environmental conditions; Among them, the hydrological data includes river water level, flow rate, flow and precipitation, and is stored in the edge node server through 5G transmission technology; the power grid load data includes power demand and load changes in each time period, and is transmitted to the central server through 5G transmission technology; the environmental meteorological data includes the meteorological temperature, humidity and rainfall of each power station, and is transmitted to the central server through 5G transmission technology.

3. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 1 is characterized by: The hydrological monitoring unit (2) comprises a hydrological dynamic analysis module and a hydrological change prediction module; Wherein, the hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data; The hydrological change prediction module predicts cross-basin hydrological changes using a hydrological prediction model based on hydrological dynamics combined with historical hydrological data.

4. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 3 is characterized by: The hydrological dynamics analysis module analyzes and monitors cross-basin hydrological dynamics in real time based on real-time hydrological data. The specific steps are as follows: S2.1.1, acquiring real-time hydrological data from the data acquisition unit (1), including river water level h(t), flow velocity v(t), flow Q(t) and precipitation P(t); S2.1.

2. Calculate the water inflow and outflow of the hydropower station as follows: Q in (t)=v in (t)×A; Q out (t)=v out (t)×A; Among them, Q in (t) is the water inflow of the hydropower station at time t; Q out (t) is the water outflow of the hydropower station at time t; A is the cross-sectional area of ​​the waterway of the hydropower station; v in (t) is the water resource inlet flow rate of the hydropower station at time t; v out (t) is the outlet flow rate of water resources of the hydropower station at time t; S2.1.

3. Calculate the dynamic change of water level in the hydropower station based on the water level change formula, as follows: Among them, Δh(t) represents the change of reservoir water level at time t; S2.1.

4. Real-time monitoring of water volume changes in the basin through the flow conservation equation, as follows: S2.1.

5. Set the warning threshold θ of the water level change rate h , if the water level change rate exceeds the warning threshold θ h An alarm is immediately triggered and fed back to the emergency dispatch unit (5) for emergency processing.

5. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 4 is characterized by: The hydrological change prediction module uses a hydrological prediction model to predict cross-basin hydrological changes based on hydrological dynamics combined with historical hydrological data. The specific steps are as follows: S2.2.

1. Obtain historical hydrological data X from the data acquisition unit (1) hist ={h(t-1),v(t-1),Q(t-1),P(t-1),…,h(tn),v(tn),Q(tn),P(tn)}, and combined with real-time hydrological data as the input data set X of the hydrological prediction model t ={h(t),v(t),Q(t),P(t),h(t-1),v(t-1),Q(t-1),P(t-1),…}; Among them, h(t-1) is the water level of the hydropower station at time t-1; v(t-1) is the water resource flow rate of the hydropower station at time t-1; Q(t-1) is the water resource flow rate of the hydropower station at time t-1; P(t-1) is the precipitation of the hydropower station at time t-1; h(tn) is the water level of the hydropower station at time tn; v(tn) is the water resource flow rate of the hydropower station at time tn; Q(tn) is the water resource flow rate of the hydropower station at time tn; P(tn) is the precipitation of the hydropower station at time tn; S2.2.

2. Obtain meteorological data Y from the meteorological forecast system t = {P forecast (t),T(t),RH(t)}, and with the dataset X t Combined with the complete input data set {X t ,Y t }; S2.2.

3. Use long short-term memory network to build a hydrological prediction model.

6. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 5 is characterized by: In S2.2.3, a long short-term memory network is used to construct a hydrological prediction model, as follows: Input layer: The input is a dataset {X t ,X t }; Hidden Layer: i t =σ(W i ·[h t-1 ,X t ]+b i ); f t =σ(W f ·[h t-1 ,X t ]+b f ); the t =σ(W o ·[h t-1 ,X t ]+b o ); Among them, W i is the input gate weight matrix; W f is the forget gate weight matrix; W o is the output gate weight matrix; b i is the input gate bias term; b f is the forget gate bias term; b o is the output gate bias term; h t-1 is the hidden layer output at time t-1; σ is the activation function; Memory unit update: in, is the candidate memory unit state; tanh(·) is the hyperbolic tangent function; W c To convert the hidden state h of the previous time step t-1 and X t Mapping to candidate memory states The weight matrix of c is the bias term; C t is the state of the memory unit at the current time t; f t is the output value of the forget gate; i t is the output value of the input gate; Final output: h t =o t *tanh(C t ); Among them, h t is the hidden layer output at time t; o t is the output gate activation value at time t; Output layer: in, is the hydrological data predicted at time t+1; W o is the weight matrix of the output layer; h t is the hidden layer output at time t.

7. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 6 is characterized by: The hydrological dispatch simulation unit (3) simulates hydrological dispatch based on the hydrological prediction model to predict the cross-basin hydrological change results and constructs a dispatch strategy for each hydropower station. The specific steps are as follows: S3.

1. Predicted cross-basin hydrological changes Calculate the total amount of available water resources W in the basin at time t+1 total (t+1), as follows: in, is the predicted inflow at time t; Predicted precipitation at time t; Predict the flow rate at time t; S3.

2. Calculate the water volume W required by the i-th hydropower station at time t+1 based on the power generation demand and historical water use data of each hydropower station. demand (i,t+1), as follows Among them, P gen (i, t+1) is the power generation of the ith hydropower station at time t+1; η is the power generation efficiency of the ith hydropower station; ρ is the density of water; g is the acceleration of gravity; is the water level of the i-th hydropower station at time t+1; S3.3, according to the water volume W required by the i-th hydropower station at time t+1 demand (i, t+1) and the total amount of available water resources in the basin at time t+1 W total (t+1), preliminary allocation of water resources is as follows: Among them, W alloc (i,t+1) is the water resource allocation of the i-th hydropower station at time t+1; μ i is the priority weight of the ith hydropower station; N is the total number of hydropower stations in the basin; S3.

4. According to the water resources allocation results W alloc (i, t+1) and the current water storage capacity of the hydropower station H(i, t), simulate the water release strategy and water storage strategy, and form a scheduling strategy, which is as follows: Water release strategy: Q out (i,t+1)=W alloc (i,t+1) / Δt; Among them, W out (i, t+1) is the water release strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step; Water storage strategy: H(i,t+1)=H(i,t)+W alloc (i,t+1)-Q out (i,t+1); Among them, H(i,t+1) is the water storage strategy of the i-th hydropower station at time t+1; Δt is the scheduling time step.

8. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 7 is characterized by: The water resource scheduling unit (4) constructs an adaptive global optimization scheduling framework, and dynamically adjusts the scheduling strategy of each hydropower station in combination with environmental meteorological data to obtain the optimal scheduling strategy for each hydropower station. The specific steps are as follows: S4.

1. Establish global optimization scheduling objective function F: S4.

2. Calculate and predict the change in water resources W at time t+1 based on future environmental meteorological data forecast (t+1): W forecast (t+1)=f(P forecast (t+1),T(t+1),RH(t+1)); Among them, P forecast (t+1) is the predicted precipitation at time t+1; T(t+1) is the predicted temperature at time t+1; RH(t+1) is the predicted relative humidity at time t+1; S4.

3. Based on the predicted water resource change at time t+1, W forecast (t+1), dynamically adjust the water resource allocation W of the i-th hydropower station at time t+1 alloc (i,t+1): W alloc (i,t+1)=W alloc (i,t)+W forecast (t+1); Among them, W alloc (i,t) is the water resource allocation of the i-th hydropower station at time t; S4.

4. Optimize water release strategy: Among them, Q' out (i, t+1) is the optimal water release strategy of the i-th hydropower station at time t+1; Q out (i, t+1) is the original water release strategy of the i-th hydropower station at time t+1; S4.

5. Optimize water storage strategy: H'(i,t+1)=H(i,t+1)+ΔH adjust (i,t+1); Among them, H'(i,t+1) is the optimized water storage strategy of the i-th hydropower station at time t+1; H(i,t+1) is the original water storage strategy of the i-th hydropower station at time t+1; ΔH adjust (i, t+1) is the water storage strategy adjustment value of the i-th hydropower station at time t+1; ΔH adjust (i,t+1)=k1·ΔW forecast (t+1)+k2·(H max (i)-H(i,t))+k3·P forecast (t+1); Among them, H max (i) is the maximum water storage capacity of the reservoir of the i-th hydropower station; k1 is the weight coefficient of the predicted value of water resources change; k2 is the weight coefficient of the reservoir water storage capacity difference; k3 is the weight coefficient of the predicted value of precipitation.

9. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 8 is characterized by: The establishment of the global optimization scheduling objective function F is as follows: Among them, α i is the weight coefficient of the power generation of the i-th hydropower station; P gen (i) is the power generation of the i-th hydropower station; β i is the weight coefficient of water resource allocation error; W alloc (i, t) is the water resource allocation of the i-th hydropower station at time t; W demand (i,t) is the water required by the i-th hydropower station at time t; N is the total number of hydropower stations in the basin; Construct water resource balance constraints: W alloc (i,t)≤W total (t); Among them, W alloc (i,t)≤W total (t) indicates that the water resources allocated to each hydropower station must not exceed the total water resources in the basin.

10. The cross-basin multi-station hydropower station centralized control optimization platform according to claim 7 is characterized by: The emergency dispatch unit (5) is used to handle water resource dispatch in emergencies and emergency situations, and includes an alarm unit and an emergency processing unit; The alarm unit is used to monitor the data of the hydrological monitoring unit (2) and the hydrological dispatch simulation unit (3) in real time. If an abnormal parameter is detected that exceeds a safe range, the system will trigger an alarm mechanism; The emergency processing unit is used to process water resource scheduling according to emergency situations, as follows: in, is the emergency water discharge of the i-th hydropower station at time t+1; H safe It is the safety water level threshold of the hydropower station.

Images