Field operation energy scheduling system based on Markov chain structure

Abstract

The invention discloses a field operation energy scheduling system based on a Markov chain structure, and relates to the technical field of battlefield energy scheduling, and the field operation energy scheduling system comprises an intelligent prediction module, an energy aggregation module, an energy routing module, a control module, a communication and monitoring module and an energy management module. The system has the advantages that the energy demand, the weather condition and the equipment state on the battlefield are monitored and predicted in real time through the intelligent prediction module, accurate prediction is performed by using the Markov chain model, dynamic networking and rapid scheduling of power resources are realized, the flexibility of a battlefield power system is improved, and the power utilization rate of the battlefield power system is improved. The system can quickly adjust power output according to real-time conditions, meets complex and changeable battlefield requirements, realizes quick transmission and distribution of electric energy through flexible configuration of the energy routing module, and further improves the response speed of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of battlefield energy scheduling, and in particular to a field energy scheduling system based on a Markov chain structure. Background Art

[0002] With the rapid development of modern warfare technology, the demand for energy utilization on the battlefield is increasing. In particular, the widespread application of new weapons and equipment such as high-energy laser weapons has put forward higher requirements for the demand and stability of electric energy. Traditional energy supply methods can no longer meet the diverse needs of modern battlefields. Therefore, energy management on the battlefield has become particularly important.

[0003] On the battlefield, renewable energy sources such as wind and solar energy, as well as electric vehicles and diesel generators, have become important sources of energy. These energy devices can not only supply power to energy equipment on the battlefield, but also achieve optimal utilization of energy through mutual coordination and scheduling. However, traditional energy management methods are often difficult to adapt to the rapid changes and uncertainties of the battlefield environment, and cannot achieve dynamic networking and rapid scheduling of energy. For this reason, we propose a field energy scheduling system based on the Markov chain structure. Summary of the invention

[0004] The purpose of the present invention is to provide a field energy scheduling system based on a Markov chain structure.

[0005] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a field energy scheduling system based on a Markov chain structure, comprising the following modules:

[0006] Intelligent prediction module, used to monitor and predict energy demand, weather conditions and equipment status on the battlefield in real time;

[0007] Energy aggregation module, which is used to integrate and dynamically aggregate various distributed power resources on the battlefield and build the aggregated power resources into a virtual power plant;

[0008] Energy routing module, which is used to realize the transmission and distribution of electric energy in the virtual electric field and can provide corresponding energy routing solutions according to different working conditions;

[0009] A control module to ensure that the virtual power plant can maintain stable operation when subjected to disturbances;

[0010] The communication and monitoring module is used to build an open communication network system suitable for virtual power plants and establish a two-way data link between the control center and each terminal device in the virtual power plant;

[0011] The energy management module is used for visual management and optimized control of the entire process of demand response of the virtual power plant on land battlefield.

[0012] As a further solution of the present invention: the intelligent prediction module includes a real-time monitoring unit and a prediction and analysis unit. The real-time monitoring unit is used to collect energy demand, weather conditions and equipment status data on the battlefield. The prediction and analysis unit can use the Markov chain model to predict future energy demand changes and new energy supply conditions. The specific prediction method is to divide the energy demand and new energy supply into different states according to the actual electricity consumption on the battlefield, count the transition probabilities between each state, and express them in the form of a state transfer matrix. The Markov chain model is trained using the collected historical data, and the trained Markov chain model and state transfer matrix are used to predict the energy demand and new energy supply status in the future.

[0013] As a further solution of the present invention: the setting of the state transfer matrix is ​​specifically that the energy demand state space is S1 = {low demand state, medium demand state, high demand state}, the new energy supply state space is S2 = {sufficient supply state, general supply state, insufficient supply state}, the energy demand state transfer matrix is ​​P1, and the new energy supply state transfer matrix is ​​P2. The specific expressions are as follows:

[0014]

[0015] Among them, P1 is a 3×3 matrix, whose element p ij represents the probability of transitioning from energy demand state i to state j, and i, j∈{1,2,3}, P2 is a 3×3 matrix whose element q mn represents the probability of transitioning from new energy supply state m to state n, and m, n∈{1,2,3}.

[0016] As a further solution of the present invention: the energy aggregation module includes a resource integration unit and a dynamic aggregation unit. The resource integration unit is responsible for integrating the wind energy, solar energy, electric drive vehicles, diesel generator sets, camp electricity and battlefield electrical equipment power resources on the battlefield. The dynamic aggregation module is used to construct the integrated resources into a virtual power plant. The dynamic aggregation module can be based on the prediction results of the prediction and analysis unit, and dynamically adjust and optimize the resources according to actual conditions.

[0017] As a further solution of the present invention: the resource integration unit integrates the above-mentioned power resources into a power resource state transfer matrix P3, which is used to describe the energy scheduling transfer probability between energy nodes S on the battlefield. The energy nodes S specifically include wind energy, solar energy, electric transmission vehicles, diesel generator sets, camp electricity and battlefield power equipment. The specific expression of the state transfer matrix is ​​as follows:

[0018]

[0019] Among them, P3 is a 6×6 matrix, whose element r xy It represents the probability that energy node x dispatches energy to energy node y, x, y∈{1, 2, 3, 4, 5, 6}, and each element in the matrix represents the probability that each energy node maintains its own energy state.

[0020] As a further solution of the present invention: the energy routing module includes a working condition judgment unit and a routing planning unit. The working condition planning unit is used to identify different combat environments, mission modes, maintenance and partial damage working conditions. The routing planning unit can formulate corresponding power transmission and distribution plans based on the Markov chain structure and the working condition judgment results.

[0021] As a further solution of the present invention: the control module includes an impedance modeling unit, a matching analysis unit and a stability control unit. The impedance modeling unit is used to establish input and output impedance models of multi-source load system parts, components and their converter branches. The matching analysis unit is used to study the matching relationship between multi-source output impedance and multi-load input impedance to find out the factors affecting system stability. The stability control unit is used to implement microgrid system impedance reshaping. The technologies used include component parameter matching optimization, active damping control and passive filtering parameter design, and the system stability is judged based on impedance matching and phase margin. If the impedance value has a matching degree greater than 0.8 and a phase margin greater than 45°, it indicates that the system is stable. If the impedance value has a matching degree less than or equal to 0.8 and a phase margin less than or equal to 45°, it indicates that the system is unstable. If the system is unstable, the damping is increased and the parameters of the passive filter are optimized.

[0022] As a further solution of the present invention: the communication and monitoring module includes a communication network construction unit, a data link unit and a monitoring and scheduling unit. The communication network construction unit is used to construct an open communication network system suitable for a virtual power plant. The data link unit is used to establish a two-way data link between the control center and each terminal device in the virtual power plant to achieve real-time data interaction. The monitoring and scheduling unit is used to monitor the terminal components of the virtual power plant and perform scheduling and coordinated control based on data feedback.

[0023] As a further solution of the present invention: the energy management module includes a visualization management unit, an analysis and prediction unit, a decision-making unit and a scheduling execution unit. The visualization management unit can realize the visualization management of the whole process of demand response of the land battlefield virtual power plant based on the high-level energy management system software architecture. The analysis and prediction unit is used to develop a virtual power plant operation control platform to analyze and predict the power generation and consumption of battlefield electricity. The decision-making unit can form battlefield power response decisions based on the analysis and prediction results and arrange the aggregate scheduling of distributed resources. The scheduling execution unit is used to implement the aggregate scheduling of distributed resources.

[0024] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0025] 1. The present invention uses an intelligent prediction module to monitor and predict energy demand, weather conditions and equipment status on the battlefield in real time, and uses a Markov chain model for accurate prediction, thereby realizing dynamic networking and rapid scheduling of power resources, improving the flexibility of the battlefield power system, and enabling the system to quickly adjust power output according to real-time conditions to meet complex and changeable battlefield needs. At the same time, through the flexible configuration of the energy routing module, rapid transmission and distribution of electric energy is realized, further improving the response speed of the system;

[0026] 2. The present invention integrates and dynamically aggregates the distributed power resources on the battlefield through the energy aggregation module, constructs a virtual power plant, and improves the overall power generation capacity and storage capacity of the power system. When facing disturbances or local damage, the control module can ensure the stable operation of the virtual power plant, and improve the source-load impedance ratio and the system stability margin through technical means such as active damping control and passive filtering parameter design. In addition, the energy routing module also has a wide adaptability, high reliability, and multi-reuse energy routing solution, which further enhances the stability and reliability of the battlefield power system;

[0027] 3. The present invention uses the energy management module to visualize and optimize the entire process of virtual power plant demand response, making energy scheduling more efficient and accurate. Based on the high-level energy management system software architecture, a virtual power plant operation control platform is developed, forming the capabilities of virtual power plant system data monitoring, power generation and power consumption analysis and prediction, battlefield power response decision-making, distributed resource aggregation scheduling, etc. This not only improves energy utilization efficiency, but also makes the energy management process more transparent and traceable, providing strong support for command decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the flow of the field energy dispatching system in an embodiment of the present invention;

[0029] Figure 2Schematic diagram of the Markov chain structure in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] The present invention provides a field energy dispatching system based on a Markov chain structure, comprising the following modules:

[0032] Intelligent prediction module, used to monitor and predict energy demand, weather conditions and equipment status on the battlefield in real time;

[0033] Energy aggregation module, which is used to integrate and dynamically aggregate various distributed power resources on the battlefield and build the aggregated power resources into a virtual power plant;

[0034] Energy routing module, which is used to realize the transmission and distribution of electric energy in the virtual electric field and can provide corresponding energy routing solutions according to different working conditions;

[0035] A control module to ensure that the virtual power plant can maintain stable operation when subjected to disturbances;

[0036] The communication and monitoring module is used to build an open communication network system suitable for virtual power plants and establish a two-way data link between the control center and each terminal device in the virtual power plant;

[0037] Energy management module, used for visual management and optimization control of the entire process of demand response of the virtual power plant on land battlefield;

[0038] In one embodiment of the present invention: the intelligent prediction module includes a real-time monitoring unit and a prediction and analysis unit. The real-time monitoring unit is used to collect energy demand, weather conditions and equipment status data on the battlefield. The prediction and analysis unit can use the Markov chain model to predict future energy demand changes and new energy supply conditions. The specific prediction method is to divide the energy demand and new energy supply into different states according to the actual electricity consumption on the battlefield, count the transition probabilities between each state, and express them in the form of a state transfer matrix. The Markov chain model is trained using the collected historical data, and the trained Markov chain model and the state transfer matrix are used to predict the energy demand and new energy supply status in the future.

[0039] In one embodiment of the present invention, the state transfer matrix is ​​specifically set as follows: the energy demand state space is S1 = {low demand state, medium demand state, high demand state}, the new energy supply state space is S2 = {sufficient supply state, general supply state, insufficient supply state}, the energy demand state transfer matrix is ​​P1, and the new energy supply state transfer matrix is ​​P2. The specific expressions are as follows:

[0040]

[0041] Among them, P1 is a 3×3 matrix, whose element p ij represents the probability of transitioning from energy demand state i to state j, and i, j∈{1,2,3}, P2 is a 3×3 matrix whose element q mn represents the probability of transitioning from new energy supply state m to state n, and m, n∈{1,2,3}.

[0042] In one embodiment of the present invention: the energy aggregation module includes a resource integration unit and a dynamic aggregation unit. The resource integration unit is responsible for integrating the wind energy, solar energy, electric drive vehicles, diesel generator sets, camp electricity and battlefield electrical equipment power resources on the battlefield. The dynamic aggregation module is used to construct the integrated resources into a virtual power plant. The dynamic aggregation module can be based on the prediction results of the prediction and analysis unit, and dynamically adjust and optimize the resources according to actual conditions.

[0043] In one embodiment of the present invention, the resource integration unit integrates the above-mentioned power resources into a power resource state transfer matrix P3, which is used to describe the energy scheduling transfer probability between energy nodes S on the battlefield. The energy nodes S specifically include wind energy, solar energy, electric transmission vehicles, diesel generator sets, camp electricity and battlefield power equipment. The specific expression of the state transfer matrix is ​​as follows:

[0044]

[0045] Among them, P3 is a 6×6 matrix, whose element r xy It represents the probability that energy node x dispatches energy to energy node y, x, y∈{1, 2, 3, 4, 5, 6}, and each element in the matrix represents the probability that each energy node maintains its own energy state.

[0046] In one embodiment of the present invention: the energy routing module includes a working condition judgment unit and a routing planning unit. The working condition planning unit is used to identify different combat environments, mission modes, maintenance and partial damage working conditions. The routing planning unit can formulate corresponding power transmission and distribution plans based on the Markov chain structure and the working condition judgment results.

[0047] In one embodiment of the present invention: the control module includes an impedance modeling unit, a matching analysis unit and a stability control unit. The impedance modeling unit is used to establish the input and output impedance models of the multi-source load system parts, components and each branch of the converter. The matching analysis unit is used to study the matching relationship between the multi-source output impedance and the multi-load input impedance to find out the factors affecting the system stability. The stability control unit is used to implement the impedance reshaping of the microgrid system. The technologies used include component parameter matching optimization, active damping control and passive filtering parameter design, and the system stability is judged based on the impedance matching degree and phase margin. If the impedance value has a matching degree greater than 0.8 and a phase margin greater than 45°, it indicates that the system is stable. If the impedance value has a matching degree less than or equal to 0.8 and a phase margin less than or equal to 45°, it indicates that the system is unstable. If the system is unstable, the damping is increased and the parameters of the passive filter are optimized.

[0048] In one embodiment of the present invention: the communication and monitoring module includes a communication network construction unit, a data link unit and a monitoring and scheduling unit. The communication network construction unit is used to build an open communication network system suitable for a virtual power plant. The data link unit is used to establish a two-way data link between the control center and each terminal device in the virtual power plant to realize real-time data interaction. The monitoring and scheduling unit is used to monitor the terminal components of the virtual power plant and perform scheduling and coordinated control based on data feedback.

[0049] In one embodiment of the present invention: the energy management module includes a visualization management unit, an analysis and prediction unit, a decision-making unit and a scheduling execution unit. The visualization management unit can realize the visualization management of the whole process of demand response of the land battlefield virtual power plant based on the high-level energy management system software architecture. The analysis and prediction unit is used to develop a virtual power plant operation control platform to analyze and predict the power generation and consumption of battlefield electricity. The decision-making unit can form battlefield power response decisions based on the analysis and prediction results and arrange the aggregate scheduling of distributed resources. The scheduling execution unit is used to implement the aggregate scheduling of distributed resources.

[0050] Embodiment 1: In a mountain combat operation, facing the complex and changeable battlefield environment, we adopted a field energy dispatching system based on Markov chain. The intelligent prediction module collected battlefield energy demand, weather and equipment status data, and used the Markov chain model to predict the energy demand state transition, such as the probability of low demand to medium and high demand. The energy aggregation module integrated solar energy, diesel generator sets and electric drive vehicle resources to form a power resource state transfer matrix, and dynamically adjusted resources according to the prediction results to ensure energy supply.

[0051] The energy routing module develops efficient energy routing solutions based on mountain terrain and mission requirements. For example, the efficiency of transmitting power through multi-node paths is increased to 85%, which is 30% higher than the traditional method. When the control module is attacked, it quickly adjusts the system parameters through stable control technology and restores stable operation within 10 minutes. The impedance matching and phase margin are both up to standard.

[0052] The communication and monitoring module monitors the status of terminal equipment in real time, ensuring real-time data interaction between the control center and energy nodes, and timely discovering and dispatching resources. The energy management module realizes visual management and optimized control, allowing commanders to intuitively understand the system status. The analysis and prediction unit accurately predicts battlefield power, and the decision-making and scheduling units work together to improve energy utilization efficiency by 25%.

[0053] Embodiment 2: In desert combat operations, facing severe weather such as sandstorms, the field energy dispatching system based on Markov chain plays a key role. The intelligent prediction module pays close attention to the impact of weather on energy supply and demand, predicts the trend of rising energy demand and declining new energy supply, and integrates diesel generator sets, camps and battlefield power equipment resources. When sandstorms affect solar power generation, the output of diesel generator sets is dynamically adjusted to ensure reasonable energy distribution. The energy routing module flexibly adjusts the transmission path. When the line is blocked by sandstorms, a new plan is quickly formulated to ensure that electric energy is transmitted to each combat unit. The control module adopts optimization technology to ensure that the system impedance matching is higher than 0.8 and the phase margin is greater than 45°, so that it can operate stably even under severe conditions. The communication and monitoring module builds a stable open communication network, monitors and adjusts the system status in real time, and the energy management module realizes visual management and optimization control, accurately predicts power generation and power consumption, and reasonably arranges resource scheduling. In this operation, system optimization control increased the reliability of energy supply by 30%, providing a solid energy backing for combat operations.

[0054] Example 3: In a high-intensity, long-term combat mission, the field energy dispatch system based on Markov chain played a key role. The intelligent prediction module accurately predicted the change of energy demand through real-time monitoring and data analysis, such as predicting that the probability of energy demand changing from medium demand to high demand is 0.6. The energy aggregation module integrates the power resources of wind energy, solar energy, electric drive vehicles and diesel generator sets to build a virtual power plant to achieve dynamic adjustment and optimization. The energy routing module flexibly adjusts the transmission and distribution of electric energy according to combat changes. The control module adopts advanced technology to ensure that the system remains stable under high load. The communication and monitoring module ensures the real-time data link and dispatch between the control center and each terminal. The energy management module improves the energy utilization efficiency by 20% through visual management, accurate prediction and efficient dispatch. The system provides solid energy support for combat missions and ensures the smooth completion of missions.

[0055] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A field energy scheduling system based on a Markov chain structure, characterized in that: Includes the following modules: Intelligent prediction module, used to monitor and predict energy demand, weather conditions and equipment status on the battlefield in real time; Energy aggregation module, which is used to integrate and dynamically aggregate various distributed power resources on the battlefield and build the aggregated power resources into a virtual power plant; Energy routing module, which is used to realize the transmission and distribution of electric energy in the virtual electric field and can provide corresponding energy routing solutions according to different working conditions; A control module to ensure that the virtual power plant can maintain stable operation when subjected to disturbances; The communication and monitoring module is used to build an open communication network system suitable for virtual power plants and establish a two-way data link between the control center and each terminal device in the virtual power plant; The energy management module is used for visual management and optimized control of the entire process of demand response of the virtual power plant on land battlefield.

2. The field energy dispatching system based on Markov chain structure according to claim 1 is characterized by: The intelligent prediction module includes a real-time monitoring unit and a prediction and analysis unit. The real-time monitoring unit is used to collect energy demand, weather conditions and equipment status data on the battlefield. The prediction and analysis unit can use the Markov chain model to predict future energy demand changes and new energy supply conditions. The specific prediction method is to divide the energy demand and new energy supply into different states according to the actual electricity consumption on the battlefield, count the transition probabilities between each state, and express them in the form of a state transfer matrix. The Markov chain model is trained using the collected historical data, and the trained Markov chain model and state transfer matrix are used to predict the energy demand and new energy supply status in the future.

3. The field energy dispatching system based on Markov chain structure according to claim 2 is characterized by: The state transfer matrix is ​​specifically set as follows: the energy demand state space is S1 = {low demand state, medium demand state, high demand state}, the new energy supply state space is S2 = {sufficient supply state, general supply state, insufficient supply state}, the energy demand state transfer matrix is ​​P1, and the new energy supply state transfer matrix is ​​P2. The specific expressions are as follows: Among them, P1 is a 3×3 matrix, whose element p ij represents the probability of transitioning from energy demand state i to state j, and i, j∈{1,2,3}, P2 is a 3×3 matrix whose element q mn represents the probability of transitioning from new energy supply state m to state n, and m, n∈{1,2,3}.

4. The field energy dispatching system based on Markov chain structure according to claim 2 is characterized by: The energy aggregation module includes a resource integration unit and a dynamic aggregation unit. The resource integration unit is responsible for integrating wind energy, solar energy, electric vehicles, diesel generator sets, camp electricity and battlefield electrical equipment power resources on the battlefield. The dynamic aggregation module is used to construct the integrated resources into a virtual power plant. The dynamic aggregation module can be based on the prediction results of the prediction and analysis unit, and dynamically adjust and optimize the resources according to actual conditions.

5. The field energy dispatching system based on Markov chain structure according to claim 4 is characterized by: The resource integration unit integrates the above-mentioned power resources into a power resource state transfer matrix P3, which is used to describe the energy scheduling transfer probability between energy nodes S on the battlefield. The energy nodes S specifically include wind energy, solar energy, electric transmission vehicles, diesel generator sets, camp electricity and battlefield power equipment. The specific expression of the state transfer matrix is ​​as follows: Among them, P3 is a 6×6 matrix, whose element r xy It represents the probability that energy node x dispatches energy to energy node y, x, y∈{1, 2, 3, 4, 5, 6}, and each element in the matrix represents the probability that each energy node maintains its own energy state.

6. The field energy dispatching system based on Markov chain structure according to claim 1 is characterized by: The energy routing module includes a working condition judgment unit and a routing planning unit. The working condition planning unit is used to identify different combat environments, mission modes, maintenance and partial damage working conditions. The routing planning unit can formulate corresponding power transmission and distribution plans based on the Markov chain structure and the working condition judgment results.

7. The field energy dispatching system based on Markov chain structure according to claim 1 is characterized by: The control module includes an impedance modeling unit, a matching analysis unit and a stability control unit. The impedance modeling unit is used to establish input and output impedance models of multi-source load system parts, components and each branch of its converter. The matching analysis unit is used to study the matching relationship between multi-source output impedance and multi-load input impedance, and find out the factors affecting system stability. The stability control unit is used to implement microgrid system impedance reshaping. The technologies used include component parameter matching optimization, active damping control and passive filtering parameter design, and the system stability is judged based on impedance matching and phase margin. If the impedance value has a matching degree greater than 0.8 and a phase margin greater than 45°, it indicates that the system is stable. If the impedance value has a matching degree less than or equal to 0.8 and a phase margin less than or equal to 45°, it indicates that the system is unstable. If the system is unstable, the damping is increased and the parameters of the passive filter are optimized.

8. The field energy dispatching system based on Markov chain structure according to claim 1 is characterized by: The communication and monitoring module includes a communication network construction unit, a data link unit and a monitoring and scheduling unit. The communication network construction unit is used to build an open communication network system suitable for virtual power plants. The data link unit is used to establish a two-way data link between the control center and each terminal device in the virtual power plant to achieve real-time data interaction. The monitoring and scheduling unit is used to monitor the terminal components of the virtual power plant and perform scheduling and coordinated control based on data feedback.

9. The field energy dispatching system based on Markov chain structure according to claim 1 is characterized by: The energy management module includes a visualization management unit, an analysis and prediction unit, a decision-making unit and a scheduling execution unit. The visualization management unit can realize the visualization management of the whole process of demand response of the land battlefield virtual power plant based on the high-level energy management system software architecture. The analysis and prediction unit is used to develop a virtual power plant operation control platform to analyze and predict the power generation and consumption of battlefield electricity. The decision-making unit can form battlefield power response decisions based on the analysis and prediction results and arrange the aggregate scheduling of distributed resources. The scheduling execution unit is used to implement the aggregate scheduling of distributed resources.

Images