A comprehensive energy management early warning system and method

Abstract

The application relates to the technical field of data processing, and discloses a comprehensive energy management early warning system and method, which comprises the following steps: firstly, scene recognition and parameter initialization are carried out according to the type of a photovoltaic power station; a multi-target optimization model is constructed, wherein the model decision variables include energy storage charging and discharging power, power generation power and power consumption load; dynamic weighting comprehensive optimization is carried out on the coefficients of the multi-target optimization model; optimization solving is carried out on the numerical values of the comprehensive optimization in step S3 to obtain the maximum value; the optimal decision variables of the discharging power, the power generation power and the power consumption load are output; and the optimal decision variables are dynamically adjusted according to the type of the photovoltaic power station, and early warning information is sent. Through dynamic optimization and scene adaptation rules, the application can timely discover operation abnormities, give early warnings, automatically adjust relevant operation data, and significantly improve the power generation efficiency, economy, safety and carbon emission reduction effect of the photovoltaic power station.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a comprehensive energy management early warning system and method. Background Technology

[0002] The current integrated energy and power management system for photovoltaic power plants has integrated multiple data fusion directions, forming a comprehensive management system with data-driven as the core and multi-objective optimization as the goal.

[0003] However, current photovoltaic (PV) power plant management systems suffer from a lack of multi-objective collaborative optimization in the power generation-storage-consumption balance: existing algorithms often focus on a single objective, such as maximum power generation, lacking collaborative optimization for multiple objectives, such as economic efficiency, safety, and carbon emission reduction. For example, if energy storage charging and discharging strategies only pursue peak-valley price arbitrage, they may ignore equipment lifespan degradation. There is also insufficient scenario differentiation: distributed PV and centralized PV differ significantly in operation and maintenance modes and fault types, but general models are difficult to adapt. For example, rooftop PV needs to consider shading, while ground-mounted power plants focus more on module aging.

[0004] Therefore, in order to address the above problems, a comprehensive energy management early warning system and method are needed. Summary of the Invention

[0005] The purpose of this invention is to provide a comprehensive energy management early warning system and method. Through dynamic optimization and scenario adaptation rules, it can promptly detect operational anomalies and automatically adjust relevant operational data, significantly improving the power generation efficiency, economy, safety, and carbon emission reduction effects of photovoltaic power plants.

[0006] This invention is implemented as follows:

[0007] This invention provides a comprehensive energy management early warning method, which is implemented according to the following steps:

[0008] S1: First, based on the type of photovoltaic power station, scene identification and parameter initialization are performed. In scene identification and parameter initialization, the photovoltaic power station type S is input first, selecting either distributed or centralized. Then, the target weight vector is constructed as follows:

[0009]

[0010] in, For the weight vector, For power generation, For economic reasons, For security reasons, For carbon emission reduction; among which, distributed photovoltaic power stations have S=1 and centralized photovoltaic power stations have S=2.

[0011] S2: Construct a multi-objective optimization model, in which the model decision variables include energy storage charging and discharging power, power generation, and electricity load;

[0012] S2.1: First, establish the objective function for maximizing power generation, as shown in the following formula:

[0013]

[0014] in, Power generation capacity; The objective function is to maximize power generation.

[0015] S2.2: Next, establish the objective function for optimizing the economics of peak-valley price arbitrage, as shown in the following formula:

[0016]

[0017] in, For energy storage charging and discharging power, For time period, The objective function is the one that optimizes the economics of peak-valley price arbitrage.

[0018] S2.3: Next, we establish the objective function that minimizes equipment lifespan loss and maximizes safety, as shown in the following formula;

[0019]

[0020] in, For deep discharge of energy storage, For component temperature fluctuation data, and The loss coefficient is... The objective function is to minimize equipment lifespan loss;

[0021] S2.4: Then establish the objective function that maximizes carbon emission reduction;

[0022]

[0023] in, Carbon emission factor of power grid;

[0024] S2.5: Establish constraints, specifically including energy storage power limits, energy storage SOC balance, and generation-consumption balance. The energy storage power limit is specifically formulated as follows:

[0025]

[0026] Energy storage SOC balance is as follows:

[0027]

[0028] The power generation-consumption balance is as follows:

[0029] ;

[0030] S3: Perform dynamic weighted comprehensive optimization on the coefficients of the multi-objective optimization model;

[0031] The coefficients of the multi-objective optimization model are dynamically weighted and optimized, as shown in the following formula:

[0032]

[0033] in, For a single target, the normalization coefficient is... The targets are economic efficiency, safety, and carbon emission reduction.

[0034] S4: Perform optimization and solve for the maximum value of the comprehensive optimization value in step S3; specifically, follow these steps:

[0035] First, update the historical best position of each particle. and the global optimal position ;

[0036] like but ;

[0037] like but ;

[0038] Then, the particle velocity and position are updated based on the individual and global optimal values. The velocity update is specifically as follows:

[0039]

[0040] The position is updated as follows:

[0041]

[0042] in, For the weight vector, , For learning factors; It is a random number;

[0043] S5: Optimal decision variables for output discharge power, power generation, and power load;

[0044] When the maximum number of iterations is reached The iteration terminates, and the globally optimal position is output. The corresponding decision variables are as follows:

[0045] .

[0046] S6: Then, based on the type of photovoltaic power station, dynamically adjust the optimal decision variables and issue early warning information. For distributed photovoltaic systems (S=1), add a shading detection module and dynamically adjust... Introduce a component health threshold; when the health level... At that time, forced reduction ;

[0047] For centralized photovoltaic systems with S=2, an additional module aging prediction model is added for dynamic adjustment. and An energy storage lifetime prediction model is introduced, when the energy storage lifetime... At that time, restrictions Fluctuation range.

[0048] Furthermore, this invention provides a comprehensive energy management early warning system, including a scene recognition and parameter configuration module; it automatically identifies the current operating scene through data from light intensity, temperature, and wind speed sensors, distributed / centralized power station types, and external data such as electricity pricing policies and weather forecasts; and dynamically adjusts and optimizes target weights based on the scene, including power generation, economic efficiency, safety, carbon emission reduction, and constraints such as energy storage SOC range and equipment lifespan threshold.

[0049] The rules engine and strategy library module dynamically adjusts and optimizes strategies based on preset rules;

[0050] Multi-objective optimization model construction module: Based on the scenario and rule engine output, dynamically construct a multi-objective optimization model that includes power generation, economic efficiency, safety, and carbon emission reduction;

[0051] Optimize the solver module, run the optimization algorithm, and solve the comprehensive objective function. The maximum value;

[0052] Decision execution and monitoring module: Transforms optimal decision variables into control commands, including energy storage charging and discharging power and power generation adjustment, monitors and tracks the decision execution effect in real time, including power generation and economic indicators, and records the deviation between actual and predicted values; then performs anomaly handling, and if the energy storage fails to respond to the command when a deviation is detected, an alarm is triggered.

[0053] Furthermore, the present invention provides a computer-storable medium storing a computer program, wherein when the computer program in the storage medium is run, it executes any one of the above-described integrated energy management early warning methods.

[0054] Compared with the prior art, the beneficial effects of the present invention are:

[0055] 1. This invention monitors the energy storage charging and discharging power, power generation power, and power load of an energy storage system, and avoids overcharging and over-discharging through dynamic weight adjustments. For example, when the energy storage SOC is below 20%, the algorithm automatically limits the discharge power, extending battery life by more than 30%. Furthermore, by charging during low electricity price periods (such as at night) and discharging during high electricity price periods (such as during the day), combined with a demand response mechanism, peak-valley arbitrage profits can be increased by 20%-40%.

[0056] Rapid fault response: By combining real-time data streams (such as abnormal current and voltage, sudden temperature changes), this invention can trigger fault warnings within 5 seconds and automatically execute data adjustment and protection strategies to reduce accident losses.

[0057] 2. This invention monitors various photovoltaic power generation data in real time according to different photovoltaic power generation sites, issues timely warnings when anomalies are detected, and dynamically adjusts the energy storage charging and discharging strategy based on abnormal environmental data according to the model.

[0058] Reduced operation and maintenance costs: Through predictive maintenance (such as component aging prediction and inverter fault early warning), algorithms can reduce unplanned downtime and lower operation and maintenance costs by 10%-20%. Attached Figure Description

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0060] Figure 1 This is a flowchart of the method of the present invention;

[0061] Figure 2 This is a system structure diagram of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to describe selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] Please see Figures 1-2 This invention provides a comprehensive energy management early warning method, which is specifically implemented according to the following steps:

[0064] S1: First, based on the type of photovoltaic power station, scene identification and parameter initialization are performed. In scene identification and parameter initialization, the photovoltaic power station type S is input first, selecting either distributed or centralized. Then, the target weight vector is constructed as follows:

[0065]

[0066] in, For the weight vector, For power generation, For economic reasons, For security reasons, For carbon emission reduction; among which, distributed photovoltaic power stations have S=1 and centralized photovoltaic power stations have S=2.

[0067] S2: Construct a multi-objective optimization model, in which the model decision variables include energy storage charging and discharging power, power generation, and electricity load;

[0068] S2.1: First, establish the objective function for maximizing power generation, as shown in the following formula:

[0069]

[0070] in, Power generation capacity; The objective function is to maximize power generation.

[0071] S2.2: Next, establish the objective function for optimizing the economics of peak-valley price arbitrage, as shown in the following formula:

[0072]

[0073] in, For energy storage charging and discharging power, For time period, The objective function is the one that optimizes the economics of peak-valley price arbitrage.

[0074] S2.3: Next, we establish the objective function that minimizes equipment lifespan loss and maximizes safety, as shown in the following formula;

[0075]

[0076] in, For deep discharge of energy storage, For component temperature fluctuation data, and The loss coefficient is... The objective function is to minimize equipment lifespan loss;

[0077] S2.4: Then establish the objective function that maximizes carbon emission reduction;

[0078]

[0079] in, Carbon emission factor of power grid;

[0080] S2.5: Establish constraints, specifically including energy storage power limits, energy storage SOC balance, and generation-consumption balance. The energy storage power limit is specifically formulated as follows:

[0081]

[0082] Energy storage SOC balance is as follows:

[0083]

[0084] The power generation-consumption balance is as follows:

[0085] ;

[0086] S3: Perform dynamic weighted comprehensive optimization on the coefficients of the multi-objective optimization model;

[0087] The coefficients of the multi-objective optimization model are dynamically weighted and optimized, as shown in the following formula:

[0088]

[0089] in, For a single target, the normalization coefficient is... The targets are economic efficiency, safety, and carbon emission reduction.

[0090] S4: Perform optimization and solve for the maximum value of the comprehensive optimization value in step S3; specifically, follow these steps:

[0091] First, update the historical best position of each particle. and the global optimal position ;

[0092] like but ;

[0093] like but ;

[0094] Then, the particle velocity and position are updated based on the individual and global optimal values. The velocity update is specifically as follows:

[0095]

[0096] The position is updated as follows:

[0097]

[0098] in, Weight vector , For learning factors; It is a random number;

[0099] S5: Optimal decision variables for output discharge power, power generation, and power load;

[0100] When the maximum number of iterations is reached The iteration terminates, and the globally optimal position is output. The corresponding decision variables are as follows:

[0101] .

[0102] S6: Then, based on the type of photovoltaic power station, dynamically adjust the optimal decision variables and issue early warning information. For distributed photovoltaic systems (S=1), add a shading detection module and dynamically adjust... Introduce a component health threshold; when the health level... At that time, forced reduction ;

[0103] For centralized photovoltaic systems with S=2, an additional module aging prediction model is added for dynamic adjustment. and An energy storage lifetime prediction model is introduced, when the energy storage lifetime... At that time, restrictions Fluctuation range.

[0104] In this embodiment, the present invention provides a comprehensive energy management early warning system, including a scene recognition and parameter configuration module; it automatically identifies the current operating scene through data from light intensity, temperature, and wind speed sensors, distributed / centralized power station types, and external data such as electricity pricing policies and weather forecasts; and dynamically adjusts and optimizes target weights according to the scene, including power generation, economic efficiency, safety, carbon emission reduction, and constraints such as energy storage SOC range and equipment lifespan threshold.

[0105] The rules engine and strategy library module dynamically adjusts and optimizes strategies based on preset rules;

[0106] Multi-objective optimization model construction module: Based on the scenario and rule engine output, dynamically construct a multi-objective optimization model that includes power generation, economic efficiency, safety, and carbon emission reduction;

[0107] Optimize the solver module, run the optimization algorithm, and solve the comprehensive objective function. The maximum value;

[0108] Decision execution and monitoring module: Transforms optimal decision variables into control commands, including energy storage charging and discharging power and power generation adjustment, monitors and tracks the decision execution effect in real time, including power generation and economic indicators, and records the deviation between actual and predicted values; then performs anomaly handling, and if the energy storage fails to respond to the command when a deviation is detected, an alarm is triggered.

[0109] In this embodiment, the present invention provides a computer-storable medium storing a computer program. When the computer program in the storage medium is run, it executes any one of the above-described integrated energy management early warning methods.

[0110] In this embodiment, a rooftop distributed photovoltaic power station is used as an example. The meteorological and power generation data are shown in Tables 1-6.

[0111] Table 1 Meteorological and power generation data

[0112]

[0113] Table 2 Electricity Price and Load Data

[0114]

[0115] Table 3 Energy Storage System Data

[0116]

[0117] Table 4 Optimized decision variables

[0118]

[0119] Table 6 Key Indicator Data

[0120]

[0121] In this embodiment, the multi-objective collaboration of the present invention, through dynamic weight adjustment, improves economic efficiency (increased peak-valley arbitrage revenue) and carbon emission reduction effect while ensuring power generation, and at the same time reduces energy storage life loss.

[0122] In terms of scenario adaptation, during periods of low light (e.g., t=1), this invention increases the carbon emission reduction weight and prioritizes the use of clean energy; during periods of low SOC in energy storage (e.g., t=18), the algorithm limits the discharge power to protect battery life.

[0123] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations will be apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A comprehensive energy management early warning method, characterized in that: Follow these steps: S1: First, based on the type of photovoltaic power station, perform scene identification and parameter initialization; In scene recognition and parameter initialization, the photovoltaic power station type S is first input, selecting either distributed or centralized; then, the target weight vector is constructed as follows: in, For vector weights, As a weight of power generation, As an economic weight, For security weights, The carbon emission reduction weights are: S=1 for distributed photovoltaic power plants and S=2 for centralized photovoltaic power plants. S2: Construct a multi-objective optimization model, in which the model decision variables include energy storage charging and discharging power, power generation, and electricity load; S3: Perform dynamic weighted comprehensive optimization on the coefficients of the multi-objective optimization model; S4: Perform optimization and solve for the maximum value of the comprehensive optimization value in step S3; S5: Optimal decision variables for output discharge power, power generation, and power load; S6: Then, based on the type of photovoltaic power station, dynamically adjust the optimal decision variables and issue early warning information; for distributed photovoltaic S=1, add a shading detection module and dynamically adjust P. pv (t), introducing a component health threshold, when the health... <H threshold At that time, P was forcibly reduced. pv (t); For centralized photovoltaic systems with S=2, an additional module aging prediction model is added for dynamic adjustment. 1 and 3. Introduce an energy storage lifetime prediction model. When the energy storage lifetime... <L threshold When, limit P ess (t) Fluctuation range; in, Power generation capacity; For energy storage charging and discharging power, For time periods.

2. The integrated energy management early warning method according to claim 1, characterized in that: In step S2, the construction of the multi-objective optimization model is performed according to the following steps: S2.1: First, establish the objective function for maximizing power generation, as shown in the following formula: in, Power generation capacity; The objective function is to maximize power generation. S2.2: Next, establish the objective function for optimizing the economics of peak-valley price arbitrage, as shown in the following formula: in, For energy storage charging and discharging power, For time period, The objective function is the one that optimizes the economics of peak-valley price arbitrage. S2.3: Next, we establish the objective function that minimizes equipment lifespan loss and maximizes safety, as shown in the following formula; in, For deep discharge of energy storage, For component temperature fluctuation data, and The loss coefficient is... The objective function with the highest security; S2.4: Then establish the objective function that maximizes carbon emission reduction; in, Carbon emission factor of power grid; The objective function that maximizes carbon emission reduction; S2.5: Establish constraints, specifically including energy storage power limits, energy storage SOC balance, and generation-consumption balance. The energy storage power limit is specifically formulated as follows: Energy storage SOC balance is as follows: The power generation-consumption balance is as follows: 。 3. The integrated energy management early warning method according to claim 1, characterized in that: In step S3, the coefficients of the multi-objective optimization model are dynamically weighted and optimized, as shown in the following formula: in, For a single target, the normalization coefficient is... The objective function is to maximize power generation. The objective function for optimizing the economics of peak-valley price spread arbitrage is... For the objective function with the highest security, The objective function is the one that maximizes carbon emission reduction.

4. The integrated energy management early warning method according to claim 1, characterized in that: In step S4, the following steps are specifically performed: First, update the historical best position p for each particle. best,i And the globally optimal position gbest; Then, the particle velocity and position are updated based on the individual and global optimal values. The velocity update is specifically as follows: The position is updated as follows: in, For the weight vector, , For learning factors; It is a random number; When the maximum number of iterations Kmax is reached, the iteration terminates, and the globally optimal position g is output. best The corresponding decision variables are as follows: 。 5. A comprehensive energy management early warning system, employing a comprehensive energy management early warning method as described in any one of claims 1-4, characterized in that: It includes a scene recognition and parameter configuration module; it automatically identifies the current operating scene by using data from light intensity, temperature, and wind speed sensors, the type of distributed / centralized power station, and external data such as electricity pricing policies and weather forecasts; and it dynamically adjusts and optimizes the target weights according to the scene, including power generation, economic efficiency, safety, carbon emission reduction, and constraints such as energy storage SOC range and equipment lifespan threshold. The rules engine and strategy library module dynamically adjusts and optimizes strategies based on preset rules; Multi-objective optimization model construction module: Based on the scenario and rule engine output, dynamically construct a multi-objective optimization model that includes power generation, economic efficiency, safety, and carbon emission reduction; Optimize the solver module, run the optimization algorithm, and solve the comprehensive objective function F. total The maximum value; Decision execution and monitoring module: Transforms optimal decision variables into control commands, including energy storage charging and discharging power and power generation adjustment, monitors and tracks the decision execution effect in real time, including power generation and economic indicators, and records the deviation between actual and predicted values; then performs anomaly handling, and if the energy storage fails to respond to the command when a deviation is detected, an alarm is triggered.

6. A computer-storable medium, characterized in that: The storage medium stores a computer program, and when the computer program in the storage medium runs, it executes the integrated energy management early warning method according to any one of claims 1-4.

Images