Emergency power supply intelligent scheduling and path planning method and system

Abstract

The invention discloses an emergency power supply intelligent scheduling and path planning method and system, and belongs to the field of emergency resource scheduling and management, and the method comprises the steps: configuring a plurality of emergency power supplies as power supply agents to form a power supply agent network, and constructing a double-layer data account book; generating a dynamic task contract based on the energy demand information; obtaining global state information from the state chain, and negotiating the dynamic task contract in combination with the energy demand information to generate a negotiation result; constructing a dynamic energy potential field according to the energy demand information and the negotiation result; planning a moving path based on the dynamic energy potential field; and updating the pre-estimated track and the real-time position as new dynamic state information to the state chain, and performing dynamic path correction. According to the technical scheme, a plurality of emergency power supplies are configured as power supply agents to form a decentralized network, and scheduling and path planning are performed through a double-layer data account book, dynamic task contract negotiation and a dynamic energy potential field, so that efficient and self-adaptive scheduling management and optimal configuration of emergency power supply resources can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of emergency resource scheduling and management, in particular to an emergency power intelligent scheduling and path planning method and system. BACKGROUND

[0002] As an important strategic resource, emergency power provides power support for the normal operation of critical infrastructure, commercial centers and residential areas in natural disasters, major accidents or power grid failures and other emergencies, and plays an irreplaceable role in maintaining social stability and reducing economic losses. Therefore, establishing an efficient and reliable emergency power scheduling and management system is an important part of modern city emergency management and business continuity planning.

[0003] In related technologies, a Chinese invention patent application with publication number CN119990652A discloses an emergency resource scheduling and path planning method, which includes: constructing a dynamic weight evaluation system based on emergency resource scheduling factors, the weight evaluation system can dynamically calculate and adjust factor weights to determine the most critical resources to be dispatched to the most needed locations in emergency situations; and constructing a deep reinforcement learning model, using historical emergency response data as a training set, so that the agent learns and optimizes the strategy of selecting the optimal path under different conditions in simulated or historical emergency scenarios.

[0004] The core defect of the above-mentioned related technology is the rigidity of the evaluation system and the static nature of the path planning. Traditional emergency resource scheduling methods rely on fixed weight evaluation systems, which cannot accurately reflect the dynamic changes of factors such as time urgency, resource demand urgency, traffic congestion, weather influence, disaster severity, affected population number and road traffic capacity in the emergency response process, resulting in limitations in optimizing resource scheduling strategies. Secondly, in terms of path planning, traditional algorithm models often plan based on static road networks and fixed traffic conditions, which cannot cope with sudden situations such as traffic congestion and road closures that may occur in actual emergency responses, which may result in suboptimal planned paths or even failure to reach the target location, thereby affecting rescue efficiency. SUMMARY

[0005] To solve the above problems, the present application provides an emergency power intelligent scheduling and path planning method and system, which adopts a technical scheme of configuring multiple emergency power supplies to form a decentralized network for power intelligent agents, and scheduling and path planning through a double-layer data ledger, dynamic task contract negotiation and dynamic energy potential field, which can realize efficient, reliable and adaptive scheduling management and optimal configuration of emergency power resources.

[0006] The above-mentioned object can be achieved by the following scheme: An emergency power intelligent scheduling and path planning method, comprising configuring multiple emergency powers as power intelligent agents to form a decentralized power intelligent agent network, and constructing a double-layer data ledger including an identity chain and a state chain, wherein the identity chain is used to record the identity information and historical credit value of each power intelligent agent, and the state chain is used to record the dynamic state information of the power intelligent agent in real time; obtaining energy demand information, and generating a dynamic task contract including a task target and an incentive weight based on the energy demand information; obtaining global state information from the state chain by the power intelligent agent, and negotiating the dynamic task contract in combination with the locally perceived energy demand information to generate a negotiation result including role assignment and deployment location; constructing a dynamic energy potential field according to the energy demand information and the deployment location in the negotiation result; planning a moving path for the power intelligent agent based on the dynamic energy potential field; in the moving process, updating the estimated trajectory and real-time position of the power intelligent agent to the state chain as new dynamic state information, and performing dynamic path correction based on the information in the state chain.

[0007] Optionally, the constructing a double-layer data ledger including an identity chain and a state chain comprises: generating identity information including a unique identity and performance parameters for each power intelligent agent, and obtaining an initial historical credit value thereof; writing the identity information and the historical credit value into the identity chain; obtaining the power, position and running state of each power intelligent agent to form dynamic state information; verifying the consistency of the dynamic state information by using a consensus mechanism, and writing the verified dynamic state information into the state chain to form global state information; encapsulating the identity chain and the state chain to construct a double-layer data ledger.

[0008] Optionally, the generating a dynamic task contract including a task target and an incentive weight comprises: collecting and analyzing local energy demand data, and identifying demand hotspot areas from the energy demand data; generating a task target code according to the coverage range and power requirement of the demand hotspot areas; calculating an incentive weight according to the importance and urgency of the task target code, and associating the task target code with the incentive weight to form the dynamic task contract.

[0009] Optionally, the generating a negotiation result including role assignment and deployment location comprises: the power intelligent agent obtains the dynamic task contract and the global state information; each power intelligent agent calculates its bid score in combination with its dynamic state information and the incentive weight of the dynamic task contract; a group consensus algorithm is executed among all power intelligent agents to determine a unique winning intelligent agent, and the role assumed by the winning intelligent agent and the corresponding deployment location are taken as the negotiation result.

[0010] Optionally, the constructing the dynamic energy potential field comprises: calculating initial potential values of regions in a preset map grid based on a spatial distribution of the energy demand information; calculating a virtual potential field gradient according to the initial potential values; introducing a local potential increment in a corresponding region according to the deployment position in the negotiation result to adjust the initial potential values, to form the dynamic energy potential field.

[0011] Optionally, the planning the moving path comprises: calculating a potential field gradient direction of a current position according to the dynamic energy potential field; generating an initial path according to the potential field gradient direction and in combination with a target deployment position; obtaining local obstacle information on a real-time advancing path through a preset sensor, and optimizing the initial path in combination with the local obstacle information to generate a final moving path.

[0012] Optionally, the dynamic path correction comprises: the power agent monitoring an estimated trajectory thereof and estimated trajectories of other power agents recorded on the state chain to identify a potential path conflict; after identifying the potential path conflict, generating a path correction contract; and performing local negotiation on the path correction contract with the power agents involved in the potential path conflict to generate a correction result, and adjusting the moving path thereof according to the correction result.

[0013] Optionally, the method further comprises: after the power agent completes a task, calculating a task completion score according to behavior data recorded on the state chain; updating a historical reputation value of the power agent in the identity chain using the task completion score; and modifying the incentive weight based on the updated historical reputation value.

[0014] Optionally, the method further comprises: judging whether there is an abnormal offline agent that has not updated dynamic state information for more than a predetermined time by monitoring the state chain; after judging that there is the abnormal offline agent, obtaining an uncompleted dynamic task contract being executed by the abnormal offline agent; decomposing the uncompleted dynamic task contract into a new dynamic task contract and triggering a new round of negotiation to realize automatic re-allocation of tasks.

[0015] Based on the same inventive concept, the present application also provides an emergency power intelligent scheduling and path planning system, comprising: a power agent configuration module configured to configure multiple emergency power supplies as power agents to form a decentralized power agent network, and to construct a double-layer data ledger comprising an identity chain and a state chain; a double-layer data ledger management module configured to obtain energy demand information, and to generate a dynamic task contract comprising a task target and an incentive weight based on the energy demand information; A dynamic task contract generation module is configured to acquire global state information from the state chain by the power supply agent, and combine local perceived energy demand information to negotiate the dynamic task contract, and generate a negotiation result containing role allocation and deployment location; A group negotiation decision module is configured to construct a dynamic energy potential field according to the energy demand information and the deployment location in the negotiation result; A dynamic potential field modeling module is configured to plan a moving path for the power supply agent based on the dynamic energy potential field; A path planning and correction module is configured to update the estimated trajectory and real-time position of the power supply agent as new dynamic state information to the state chain during movement, and perform dynamic path correction based on information in the state chain.

[0016] Compared with the prior art, the present application has the following advantages: 1. By constructing a decentralized network based on a double-layer data ledger, an unalterable identity and reputation profile is established for all participating power supply agents, and the global consistency and credibility of state information are ensured through a consensus mechanism. This design solves the problem of information opacity and lack of trust in traditional scheduling systems, providing a solid trust foundation for subsequent autonomous negotiation and collaborative work, making the entire scheduling management process transparent, auditable and highly reliable.

[0017] 2. A dynamic task contract containing incentive weights and a group consensus-based bidding negotiation mechanism are introduced, which converts emergency tasks into standardized, valuable digital contracts, and drives power supply agents to autonomously bid according to their own capabilities and task values. This market-oriented resource allocation mode replaces the rigid command-based scheduling, enabling limited emergency power resources to be adaptively and dynamically configured according to the importance and urgency of tasks, improving resource utilization efficiency and economic benefits of emergency response.

[0018] 3. A method of integrating advanced scheduling decisions with underlying path planning is proposed, which converts complex task objectives into clear navigation gravitational fields by constructing a dynamic energy potential field, guiding power supply agents to make macroscopic path choices. At the same time, combined with trajectory sharing and local negotiation on the state chain, autonomous obstacle avoidance and collaborative traffic among multiple agents are realized, ensuring efficient and safe execution at the logistics execution level, making resource deployment not only scientifically decision-making, but also intelligent and smooth execution process.

[0019] 4. Through continuous monitoring of the state chain, an automatic fault discovery and task reassignment mechanism is established. When an abnormal offline of a single power supply agent occurs, the mechanism can quickly identify and reissue the unfinished tasks of the single power supply agent to the network, triggering a new round of distribution process, so as to realize self-healing and service continuity guarantee of the system. This design enhances the robustness and task completion ability of the entire emergency power management system in complex and harsh environments.

[0020] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0022] Figure 1 is a flowchart of an emergency power intelligent scheduling and path planning method according to an embodiment of the present application.

[0023] Figure 2 is a dynamic task contract generation and incentive weight calculation schematic diagram of an emergency power intelligent scheduling and path planning method and system according to an embodiment of the present application.

[0024] Figure 3 is a dynamic energy potential field and mobile path planning schematic diagram of an emergency power intelligent scheduling and path planning method and system according to an embodiment of the present application.

[0025] Figure 4 is a structural schematic diagram of an emergency power intelligent scheduling and path planning system according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0027] REFERENCE Figure 1An embodiment of the present application provides an emergency power intelligent scheduling and path planning method, which adopts a technical scheme of configuring multiple emergency powers as power intelligent agents to form a decentralized network, and scheduling and path planning through a double-layer data ledger, dynamic task contract negotiation and dynamic energy potential field, so that efficient, reliable and self-adaptive scheduling management and optimal configuration of emergency power resources can be realized.

[0028] The method of the embodiment specifically comprises: Configuring multiple emergency powers as power intelligent agents to form a decentralized power intelligent agent network, and constructing a double-layer data ledger comprising an identity chain and a state chain, wherein the identity chain is used to record identity information and historical credit values of each power intelligent agent, and the state chain is used to record dynamic state information of the power intelligent agents in real time; Obtaining energy demand information, and generating a dynamic task contract comprising a task target and an incentive weight based on the energy demand information; The power intelligent agents acquire global state information from the state chain, and negotiate the dynamic task contract in combination with locally perceived energy demand information to generate a negotiation result comprising role allocation and deployment positions; According to the energy demand information and the deployment positions in the negotiation result, a dynamic energy potential field is constructed; The power intelligent agents plan a moving path based on the dynamic energy potential field; In the moving process, the power intelligent agents update estimated trajectories and real-time positions as new dynamic state information to the state chain, and perform dynamic path correction based on information in the state chain.

[0029] Specifically, a decentralized emergency power supply scheduling framework based on multi-agent technology is constructed. The core is to give each emergency power supply an agent identity, and provide a trust basis and real-time global situation awareness for the network through a double-layer data ledger containing an identity chain and a state chain. On this basis, external energy demand is abstracted as a dynamic task contract with incentive weight, driving each power supply agent to conduct decentralized negotiation based on shared state information, and determining the task performer and deployment location in a market-oriented bidding manner. To solve the path planning problem, discrete scheduling decisions are converted into continuous dynamic energy potential field, and the potential field gradient is used to guide the agent for macro path planning. At the same time, by sharing the estimated trajectory on the state chain, a multi-agent collaboration mechanism is established, enabling agents to actively identify and negotiate potential path conflicts during movement, thereby integrating high-level task objectives, group collaboration, and underlying motion control into a complete closed-loop autonomous scheduling logic from task generation, decision allocation to path execution and dynamic correction. Through the decentralized architecture design, the dependence on the central scheduling server is eliminated, avoiding single point failure risk and improving the robustness and scalability of the entire emergency power supply system. The introduction of the double-layer data ledger not only ensures the credibility of each agent's identity and the traceability of its behavior, but also builds a unified and real-time information sharing platform through the state chain, laying a solid data foundation for autonomous collaboration among agents. The decision mechanism based on dynamic task contract and group negotiation realizes the intelligent and market-oriented allocation of emergency resources, enabling resources to adaptively flow to the areas with the highest value, improving scheduling efficiency and accuracy. The combination of dynamic energy potential field and real-time path correction ensures that the power supply agent has a clear global goal orientation in the navigation under complex dynamic environment, and has the micro adaptive ability to cope with local obstacles and group conflicts, thereby comprehensively improving the speed, safety and success rate of task execution of emergency response.

[0030] Optionally, the double-layer data ledger containing an identity chain and a state chain comprises: generating identity information containing a unique identity and performance parameters for each power supply agent, and obtaining an initial historical credit value thereof, and writing the identity information and the historical credit value into the identity chain; obtaining the power, position and running state of each power supply agent to form dynamic state information; adopting a consensus mechanism to verify the consistency of the dynamic state information, and writing the verified dynamic state information into the state chain to form global state information; encapsulating the identity chain and the state chain to construct a double-layer data ledger.

[0031] Specifically, the digital identity of each emergency power supply as a power supply agent is initialized. This process generates a unique and tamper-proof unique identity for each power supply agent, which can be created based on the public key of an asymmetric encryption algorithm. At the same time, a digital description of its physical performance is formed, which includes a set of performance parameters such as rated power, battery capacity, maximum moving speed, etc. The two parts together constitute the core identity information of the power supply agent. In addition, an initial historical reputation value is set for the power supply agent. Subsequently, the identity information including the unique identity, performance parameters and initial historical reputation value is packaged and recorded in the identity chain after network consensus. The identity chain as a distributed ledger ensures the permanence and tamper resistance of the identity information. Secondly, during the running process, each power supply agent periodically collects its real-time data through its internal sensors and control units, such as battery management system BMS and global positioning system GPS, including remaining power, accurate geographic location coordinates and working mode such as standby, moving or power supply running state. These data are combined to form the dynamic state information of the agent. When a power supply agent needs to update its state, it will broadcast this dynamic state information to other power supply agents in the network. After receiving the information, other nodes in the network will start the consensus mechanism, which is a rule that all nodes in the network follow to ensure data consistency, such as the practical Byzantine fault tolerance algorithm PBFT suitable for Internet of Things environment. Through this mechanism, a certain number of nodes cross-verify the received dynamic state information to confirm its legitimacy, timeliness and logic. Only when more than a preset threshold number of agents agree that the state information is valid, the information will be approved to be written into a new block of the state chain, where the preset threshold is two-thirds of the number of all agents. All verified dynamic state information on the state chain is collectively gathered into a global state information shared by the whole network and updated in real time. The identity chain and the state chain are logically encapsulated to build a complete two-layer data ledger. The specific implementation is that each record in the state chain contains the unique identity of the power supply agent that generates the state information. Any query of dynamic state information can be traced back to the corresponding and trusted static identity information in the identity chain through the identity, thereby binding dynamic behavior with trusted entities to form a clear structure and data trusted decentralized data management foundation.

[0032] For example, there is an existing network containing 10 emergency power supplies. Take the emergency power supply numbered EPS001 as an example, its public key and private key stored only in the power supply agent are generated using an elliptic curve encryption algorithm such as secp256k1. The public key will serve as the unique identity of EPS001. At the same time, we also need to define the set of physical performance parameters of EPS001, such as rated power of 10kW, battery capacity of 50kWh, maximum moving speed of 5m / s, and an initial historical reputation value of 0.5 (range 0-1). These information will be packaged, and more than 2 / 3 of the nodes need to reach an agreement through network consensus, for example, using the practical Byzantine fault tolerance algorithm PBFT, when 7 nodes in the network agree on the genesis block, it is recorded in the identity chain. Thereafter, EPS001 will periodically collect its own data through the battery management system BMS and the global positioning system GPS. For example, at T=5 minutes, the collected data includes the remaining power of 45kWh, the geographic position coordinates, and the running state of power supply. These data will be combined into dynamic state information and broadcast to the network. Other nodes in the network, such as EPS002, EPS003, etc., will cross-verify after receiving this information. If more than 5 of the 7 nodes confirm that the state information is valid, the information will be written into a new block in the state chain. Each record on the state chain contains the unique identity public key of EPS001, which is associated with the identity chain, ensuring the traceability and security of the data.

[0033] Optionally, the generating of the dynamic task contract containing task objectives and incentive weights comprises: Collecting and analyzing local energy demand data, identifying demand hotspot areas from the energy demand data; Generating task objective codes according to the coverage and power requirements of the demand hotspot areas; Calculating incentive weights according to the importance and urgency of the task objective codes, and associating the task objective codes with the incentive weights to form the dynamic task contract.

[0034] Specifically, by accessing various information sources such as city emergency command centers, power dispatching networks, or Internet of Things sensors, local energy demand data is continuously collected and analyzed, including power outage incident reports, user assistance information, and power consumption warnings for important facilities. By analyzing these geospatially tagged data in real time, such as using the density-based spatial clustering algorithm DBSCAN or defining geographic grids for demand density statistics, energy demand hotspots are automatically identified, i.e., areas with high concentration of energy demand. For each identified energy demand hotspot, a task target code is generated based on its specific energy consumption characteristics. The task target code is a structured data object whose content clearly defines the core requirements of the task, such as the central geographic coordinates of the area, the required coverage radius or polygon range, and the minimum power required to ensure the basic operation of the area. For example, the demand hotspot of a hospital will include the precise location of the hospital, the range of key buildings that must be covered, and the power in kilowatts required to maintain core medical equipment. To quantify the priority level of the task, the system calculates a corresponding incentive weight. The incentive weight takes into account the importance and urgency of the task. Specifically, it is calculated according to the following formula: ; wherein represents the total incentive weight of the dynamic task contract. is the normalized task importance value, which is determined according to the nature of the demand hotspot area, such as hospitals, communication base stations, and other critical infrastructure, which are assigned higher importance initial values, while ordinary residential areas have relatively lower importance values, which are then mapped to a standard interval such as 0 to 1 by a function. is the normalized task urgency value, which can be dynamically calculated based on the duration of power outage, the estimated recovery time, or the urgency of the demand submission time, for example, a region that has been out of power for several hours will have a higher urgency value than a region that has just reported a demand, and this value is also normalized. α and β are preset weight coefficients, and α plus β equals 1, used to adjust the relative proportion of importance and urgency in the final incentive weight calculation, and can be adjusted according to the macro strategy to focus on protecting critical targets or responding to the most urgent demands. The task target code generated above is associated with the calculated incentive weight, and both are packaged into an unalterable digital contract, i.e., a dynamic task contract, which is published to the power agent network for all power agents to obtain and use as a basis for subsequent negotiation decisions. The dynamic task contract generation process is shown in FIG. 2, which identifies geospatial demand hotspots, normalizes task importance and urgency, and calculates the incentive weight to provide a quantitative basis for agent bidding.

[0035] Exemplarily, by analyzing the data of the city emergency command center, it is identified that a hospital area has a high concentration of energy demand due to power failure. The system generates a task target code for the area, which includes the central geographic coordinates, a coverage radius of 200 m, and a minimum power requirement of 5 kW. To quantify the priority level of the task, the corresponding incentive weight is calculated. The importance of the hospital is initially set to 0.8, and the duration of the power failure is 2 hours. First, the importance needs to be normalized, using linear normalization to map [0, 1] to [0, 1], so = 0.8. Second, the urgency is normalized using a sigmoid function: where k is the steepness factor (e.g., k = 1), t is the power failure time of 2 hours, and t_0 is the reference time of 1 hour. The calculation results in . With α = 0.6 and β = 0.4, the total incentive weight . Finally, the task target code and the incentive weight are packaged into a dynamic task contract and published to the network for all power supply agents to obtain.

[0036] Optionally, the generation of the negotiation result including role assignment and deployment location comprises: the power supply agent obtains the dynamic task contract and the global state information; each power supply agent calculates its bid score by combining its dynamic state information and the incentive weight of the dynamic task contract; a group consensus algorithm is executed among all power supply agents to determine a unique winning agent, and the role and corresponding deployment location assumed by the winning agent are taken as the negotiation result.

[0037] Specifically, when a new dynamic task contract is published to the decentralized power supply agent network, all power supply agents in standby or assignable state will actively obtain this contract. At the same time, each power supply agent obtains the global state information containing the latest power, location and running state of all other agents by accessing the state chain. Second, after obtaining the task information, each power supply agent will enter a local decision evaluation stage. It will match and calculate its own dynamic state information, i.e., the current power, location, etc., with the incentive weight and task target contained in the dynamic task contract to obtain its bid score for the task. The bid score is a comprehensive evaluation index, which can be quantified by the following formula: ; In this formula, is the final bid score of the i-th power supply agent. is the incentive weight of the dynamic task contract, which is directly obtained from the contract and represents the value of the task. is the energy matching score, which is calculated by the available energy of the power agent itself and the required power of the task and the expected service time. The more sufficient the available energy is, the higher the score is. is the distance cost score, which is calculated by the distance between the current location of the power agent and the deployment location of the task target. The closer the distance is, the higher the score is. is the reputation score, which is directly derived from the historical reputation value recorded in the identity chain. The higher the reputation is, the higher the score is. , , is the preset normalized weight coefficient, which is used to balance the importance of energy, distance and reputation in bidding. Their sum is 1. Through the formula, each power agent converts its multi-dimensional capabilities and state into a single, comparable bid score. In order to determine a unique task executor among all competitors, the network will execute a group consensus algorithm on all bid scores submitted by the agents. Each agent will broadcast its calculated bid score to the entire network. After receiving all other participants' bid scores, all agents will independently execute a deterministic selection algorithm locally, for example, simply selecting the agent with the highest score as the winner. Since all agents have the same input data, i.e. all bid scores, and follow the same selection rules, they will deterministically reach a unique consensus, i.e. jointly confirm the same winning agent. The winning agent will be assigned the role of task executor, and the deployment location it needs to go to is the location specified in the dynamic task contract. These two pieces of information together constitute the final negotiation result of this negotiation.

[0038] Exemplarily, after the dynamic task contract is published, the power agent network needs to negotiate to determine the specific task executor. EPS001, EPS002 and EPS003 have obtained the above dynamic task contract, and their respective state information is as follows: the power of EPS001 is 45kWh, the location is 1, and the reputation value is 0.6; the power of EPS002 is 30kWh, the location is 2, and the reputation value is 0.8; the power of EPS003 is 55kWh, the location is 3, and the reputation value is 0.7. Each power agent needs to calculate its bid score. First, the energy matching score is calculated. The task requires 5kW power for 2 hours, so it requires 10kWh power. A linear proportion is used: =45 / 10=4.5, since the score cannot exceed 1, it is taken as 1, =30 / 10=3, since the score cannot exceed 1, it is taken as 1, =55 / 10=5.5, since the score cannot exceed 1, it is taken as 1. Second, the distance cost score is calculated. An inverse proportional function where k is a distance sensitivity parameter taking a default value k = 1000. The distance is calculated as: . The initial potential value of each grid cell is calculated as . The initial potential value of each grid cell is calculated as . The bidding score is calculated as . Since EPS002 has the highest score, it is assigned the role of task performer and its deployment location is.

[0039] Optionally, the constructing the dynamic energy potential field comprises: calculating the initial potential value of each region in the preset map grid based on the spatial distribution of the energy demand information; calculating the virtual potential field gradient according to the initial potential value; introducing a local potential increment in the corresponding region according to the deployment location in the negotiation result to adjust the initial potential value, to form the dynamic energy potential field.

[0040] Specifically, the entire emergency response geographical area is preset to be gridded on a digital map, i.e., a continuous two-dimensional space is discretized into individual grid cells, each of which has a unique coordinate identifier. Then, based on the spatial distribution characteristics of the obtained energy demand information, the initial potential value of each grid cell is calculated. Specifically, the total amount or density of energy demand falling within each grid cell is counted, and it is mapped to the initial potential value of the cell through a preset function. In this model, we define the potential as a scalar field representing demand attraction. The higher the demand in a region, the higher the initial potential value, thereby forming an initial potential field reflecting the global energy demand distribution. Subsequently, according to the initial potential value distribution, the virtual potential field gradient covering the entire map can be calculated. The gradient at any point points in the direction of the fastest potential growth, i.e., the direction of the fastest demand growth. After completing the construction of the above-mentioned basic potential field, according to the negotiation result output by the group negotiation decision module, the target deployment location of the unique winning agent determined therein is extracted. In order to guide the winning agent to move accurately to this specific target, a local potential increment is introduced in the grid cell corresponding to the deployment location and its adjacent regions to adjust the initial potential value of the region. This increment is a numerical value greater than the potential peak value of the surrounding region, and its role is to make the target deployment location a strong attractive pole in the entire potential field. The final dynamic energy potential field can be represented as: ; In this formula, p represents any position point on the map. U(p) is the final dynamic potential value of the position point. is the initial potential value of the position point determined by the global energy demand information, which is a function of the demand density of the region where the point is located. is a local potential energy increment function introduced at the negotiation-determined deployment location, which takes the maximum value when p is equal to the negotiation-determined deployment location, and quickly decays with the increase of the distance from the negotiation-determined deployment location, forming a potential energy peak centered on the deployment location. Through such superposition adjustment, a dynamic energy potential field is constructed, which not only reflects the global demand situation, but also highlights the current highest priority task target.

[0041] Exemplarily, in order to guide the power source agent to effectively reach the target location, it is necessary to construct a dynamic energy potential field. The area of 500mx500m around the hospital is divided into a 10mx10m grid, and the energy demand density density in a certain grid unit (i,j) is 0.2kW / m^2. The demand density is mapped to the initial potential energy value using linear scaling: (i,j)=k*density, where k is the scaling factor, such as 10, then A local potential energy increment is introduced in the grid unit corresponding to the deployment location and its adjacent area, using a Gaussian function: where A is the peak amplitude (for example, A=100), and is the standard deviation (for example = =20m). At the deployment location , at a location 10m away from the deployment location (x,y)≈93.9. The final dynamic energy potential field is .

[0042] Optionally, the planned moving path comprises: calculating the potential field gradient direction of the current location according to the dynamic energy potential field; generating an initial path according to the potential field gradient direction and in combination with the target deployment location; obtaining local obstacle information on the real-time moving path through a pre-set sensor, and optimizing the initial path in combination with the local obstacle information to generate the final moving path.

[0043] Specifically, the winning agent calculates the gradient direction of the dynamic energy potential field at its current position according to the dynamic energy potential field constructed by the dynamic potential field modeling module. The gradient is a vector, the direction of which points to the direction in which the potential energy value of the dynamic energy potential field increases the fastest, which is equivalent to the direction of the maximum attractive force that the power agent receives in the physical sense. The attractive force contains both the traction of the global demand distribution and the strong pointing to the specific deployment location. Secondly, the power agent takes the gradient direction of the potential field as the basic navigation vector and combines it with the target deployment location it eventually wants to reach to generate an initial path through iterative calculation. This process can be regarded as a gradient climbing process. The power agent moves a small distance along the current gradient direction at each step and repeatedly does so. All moving steps are connected to form an idealized initial path from the starting point to the deployment location, which guarantees the strategy of advancing towards the highest value target in a macroscopic sense. Then, in the process of moving along the initial path, the power agent scans the physical environment in front of and around the path in real time and at a high frequency through its preset sensors, such as lidar, high-definition camera or ultrasonic sensor array, to obtain information about local obstacles such as sudden traffic congestion, temporary roadblocks or debris not marked on the map. Once a local obstacle is detected, the initial path is dynamically optimized by the path planning algorithm. This optimization process can introduce the concept of repulsive force. Each obstacle will generate a virtual repulsive force field around it, and the size of the force field is inversely proportional to the distance between the power agent and the obstacle. The next movement decision of the power agent will be determined by the vector sum of the attractive force and the repulsive force. The motion vector of the power agent can be represented as: ; wherein, is the motion vector of the power agent at the next time. is the attractive vector calculated based on the gradient of the dynamic energy potential field, the direction of which points to the direction in which the potential energy increases the fastest, guiding the agent towards the target. is the total repulsive vector generated by the detected local obstacles, the direction of which is away from the obstacles, used to avoid collisions. and are preset gain coefficients used to adjust the relative weights of the attractive force and the repulsive force. By solving this vector sum in real time, a smooth curve is generated that avoids obstacles and re-approaches the original target. This constantly dynamically optimized trajectory is the final movement path. The dynamic energy potential field and the path planning effect are shown in FIG. 3. The initial potential field reflects the global demand, the target location forms a potential energy peak, the agent moves along the gradient direction and avoids obstacles to achieve precise deployment.

[0044] Exemplarily, the winning power agent needs to plan a moving path according to the dynamic energy potential field. The EPS002 starts planning the path from its current position, first calculates the gradient direction of the potential field at this position. The gradient of the potential field in the x direction is dU / dx, and the gradient in the y direction is dU / dy. The gradient can be calculated by numerical methods, such as finite difference method. The calculated gradient direction vector is (0.1, -0.2). The EPS002 takes this gradient direction as the basic navigation vector, iteratively generates the initial path, and moves a small distance such as 1 m along the gradient direction at each step until it approaches the deployment position. In the process of traveling along this initial path, the EPS002 scans the environment in front by laser radar and detects an obstacle 5 m away, which generates a repulsive force field. The repulsive force is inversely proportional to the distance: wherein is the repulsive force coefficient = 10, then the repulsive force vector direction is away from the obstacle, and the size is 10 / 5 = 2. , then the next motion vector . The EPS002 moves along this vector direction to bypass the obstacle.

[0045] Optionally, the dynamic path correction includes: The power agent monitors its estimated trajectory and the estimated trajectory recorded by other power agents on the state chain to identify potential path conflicts; After identifying the potential path conflict, a path correction contract is generated; The power agent involved in the potential path conflict locally negotiates the path correction contract, generates a correction result, and adjusts its moving path according to the correction result.

[0046] Specifically, based on the power agent that is performing a mobile task, the estimated trajectory information of all other power agents that are moving is continuously read and monitored from the state chain. The estimated trajectory information is a series of future time points and their corresponding predicted location coordinates that each power agent uploads to the state chain after planning its moving path. The power agent will perform a spatio-temporal cross-analysis of its own estimated trajectory with all other estimated trajectories obtained from the state chain. When it is predicted that at a certain time point in the future, the predicted location of the power agent will be less than a preset safety threshold away from the predicted location of another power agent, it is determined that a potential path conflict is identified. Secondly, after identifying a potential path conflict, the monitoring power agent will immediately generate a path correction contract. The contract is a standardized data structure that contains the unique identity of the conflicting parties, the time and geographic coordinates at which the conflict is predicted to occur, and the task priority of the initiating party, among other information. The contract is sent directly to the other power agent involved in the potential path conflict. Then, the two parties that receive the path correction contract enter a local, point-to-point negotiation phase. They do not need to broadcast throughout the network, but only communicate between the conflicting parties. The decision of the negotiation is based on a set of preset, deterministic rules to achieve fast decision-making, such as comparing the incentive weights of the dynamic task contracts that the two parties are performing, with the party having a lower incentive weight assuming the responsibility of avoidance; or in the case of equal weights, comparing the historical reputation values of the two parties, with the party having a lower reputation value assuming the responsibility of avoidance. The result of the negotiation, i.e. which party to adjust the path, is the correction result. Finally, according to the correction result produced by the negotiation, the power agent that assumes the responsibility of avoidance will immediately adjust its moving path, such as by temporarily reducing speed, pausing to wait, or deviating slightly from the original path to avoid the conflict point. The new moving path after the adjustment will generate a new estimated trajectory, which will be immediately updated to the state chain by the agent, thus completing the dynamic path correction.

[0047] For example, in order to avoid collisions between multiple power agents during movement, dynamic path correction is needed. When EPS002 monitors the estimated trajectory of EPS004 and predicts that it may conflict with its own estimated trajectory in 2 minutes, the distance is less than 5m. EPS002 generates a path correction contract, which contains the identities of the two parties, the conflict time and coordinates, and its own task priority. After receiving the contract, EPS004 negotiates with EPS002. Assuming that the negotiation rule is to compare the task priorities, and the task priority of EPS004 is lower, then EPS004 assumes the responsibility of avoidance. EPS004 temporarily reduces the speed, waits for 1 minute to avoid the conflict point, and then restores the original speed, thus avoiding the potential collision.

[0048] Optionally, the method further comprises: After the power agent completes the task, a task completion score is calculated based on the behavior data recorded in the state chain. updating the historical reputation value of the power agent in the identity chain based on the task completion score; modifying the incentive weight based on the updated historical reputation value.

[0049] Specifically, after the power agent completes the work specified in a dynamic task contract, such as providing power for a specified duration at the target deployment location, a task evaluation program is initiated. This program retrieves and analyzes all behavior data recorded by the power agent during the execution of this task by accessing the state chain, which constitutes a complete digital footprint of its behavior, including whether it arrived at the deployment location on time, whether the power output during the power supply process was stable and met the requirements, and whether it effectively complied with the path coordination rules, etc. Based on these objectively recorded behavior data, a comprehensive task completion score is calculated through a multi-dimensional evaluation model. This score can be quantified as follows: ; wherein, represents the final task completion score. f is a pre-set scoring function. is the timeliness index of the task, obtained by comparing the actual arrival time recorded in the state chain with the deployment time required by the contract. is the quality index of the task, which evaluates the stability and accuracy of the actual power supply power curve recorded in the state chain by comparing it with the power value required by the contract. is the compliance index of the task, which judges whether there are irregularities such as improper handling of path conflicts by checking the behavior records in the state chain. These indicators are quantified and aggregated after weighting to generate a standardized task completion score. Secondly, this calculated task completion score will be used to update the historical reputation value recorded in the identity chain of the power agent. This updating process is not a simple replacement, but a smoothing update mechanism to reflect its long-term performance. Its update formula can be expressed as: ; wherein, is the updated historical reputation value, is the old historical reputation value stored in the identity chain, is the task completion score of this time, is an update factor between 0 and 1, which is used to control the degree of influence of single task performance on the overall reputation. The updated historical reputation value will be packaged and written into the identity chain, realizing the permanent update of the reputation profile of the power agent. Based on the completion of the task and the updated historical reputation value, the dynamic incentive weight generation strategy is dynamically modified. Specifically, the system will analyze the relationship between the task completion score and the initial incentive weight. If the task with high incentive weight is often failed to be executed by the agent with low reputation value, the base incentive weight of the future dynamic task contract of the same type of task will be further increased to attract agents with higher reputation and stronger ability to participate in bidding. On the contrary, if some tasks are always successfully completed, the incentive weight will be adjusted appropriately, so as to realize the optimal allocation of incentive resources.

[0050] Exemplarily, after the power agent completes the task, it needs to be evaluated and its reputation value is updated. After EPS002 completes the power supply task, the system evaluates its behavior data. Assuming that EPS002 arrives on time, the power supply is stable, but a slight path conflict occurs. Then the on-time degree on-time, quality power stability, compliance slight conflict. The scoring function is linear weighting: wherein = 0.4, = 0.4, = 0.2, then = 0.4*1+0.4*0.9+0.2*0.8=0.92. Update the historical reputation value, assuming that γ = 0.1, , . The system will write into the identity chain to complete the reputation update.

[0051] Optionally, the method further comprises: by monitoring the state chain, it is judged whether there is an abnormal offline agent that has not updated the dynamic state information for more than a predetermined time; after judging that there is the abnormal offline agent, an unfinished dynamic task contract being executed by the abnormal offline agent is obtained; the unfinished dynamic task contract is decomposed into a new dynamic task contract and a new round of negotiation is triggered to realize automatic reallocation of the task.

[0052] Specifically, each power smart agent or a dedicated monitoring node in the network will continuously perform health checks by monitoring the state chain. All the latest dynamic state information of the power smart agents on the state chain is traversed, and special attention is paid to the timestamp attached to each information entry. A reasonable time threshold, for example, several minutes, is set, which represents the normal maximum interval for the power smart agent to update its state. If the latest record timestamp of a power smart agent on the state chain exceeds the predetermined time threshold from the current time, the smart agent will be marked as an abnormal offline smart agent. Secondly, once an abnormal offline smart agent is determined through the above monitoring, the subsequent fault-tolerant processing flow is started. The unfinished dynamic task contract that the abnormal offline smart agent undertook before going offline and recorded on the state chain is queried. By accessing the state chain and possibly the contract repository, the key information of the unfinished task, such as the target and remaining workload, is accurately obtained. For example, if a task is to provide power for two hours and the smart agent goes offline after one hour, the unfinished dynamic task contract is the remaining one-hour power supply task. Then, this unfinished dynamic task contract is processed, decomposed or directly converted into a new dynamic task contract, which is deployed at the same location and the incentive weight is dynamically adjusted according to the urgency. This newly generated dynamic task contract is immediately published to the power smart agent network, thereby automatically triggering a new round of group negotiation decision-making process to achieve seamless and automatic reallocation of tasks.

[0053] For example, in order to ensure the reliability of the system, abnormal situations need to be handled and tasks need to be automatically reallocated. Assume that EPS005 goes offline after providing power for 1 hour, and the latest record timestamp of EPS005 on the state chain exceeds 5 minutes from the current time. EPS005 is marked as an abnormal offline smart agent. Query the unfinished task contract undertaken by EPS005 and find that the remaining power supply time is 1 hour. A new contract requiring power supply for 1 hour is generated, which is deployed at the same location but the incentive weight is increased by 10%. The new contract is published to the network, triggering a new round of negotiation and decision-making, thereby achieving automatic reallocation of tasks and ensuring the continuity of energy supply.

[0054] Reference Figure 4 Based on the same inventive concept, the present application also provides an emergency power smart scheduling and path planning method system, which comprises: A power smart agent configuration module is configured to configure multiple emergency power supplies as power smart agents to form a decentralized power smart agent network and build a double-layer data ledger including an identity chain and a state chain. A double-layer data ledger management module is configured to obtain energy demand information and generate dynamic task contracts including task targets and incentive weights based on the energy demand information. A dynamic task contract generation module is configured to acquire global state information from the state chain by the power supply agent, and negotiate the dynamic task contract in combination with locally perceived energy demand information, to generate a negotiation result containing role assignment and deployment location; A group negotiation decision module is configured to construct a dynamic energy potential field according to the energy demand information and the deployment location in the negotiation result; A dynamic potential field modeling module is configured to plan a moving path for the power supply agent based on the dynamic energy potential field; A path planning and correction module is configured to update the estimated trajectory and real-time position of the power supply agent to the state chain as new dynamic state information during movement, and perform dynamic path correction based on information in the state chain.

[0055] It should be noted that the electrical connection between the above-mentioned various units does not necessarily represent the direct connection of the line, the indirect connection mode, as long as the purpose of the application is achieved, which is applicable to the embodiments of the application. The above-described is only an exemplary embodiment of the application, and cannot limit the scope of the application.

[0056] That is, any equivalent changes and modifications made in accordance with the teachings of the present application are still within the scope of the present application. Other embodiments of the present application will be readily apparent to those skilled in the art upon considering the specification and practice of the true principles disclosed herein. The present application is intended to cover any variations, uses, or adaptive changes to the present application that follow the general principles of the present application and include common knowledge or conventional technical means in the art not disclosed by the present application.

Claims

1. An intelligent scheduling and path planning method for emergency power supplies, characterized in that, The method includes: Multiple emergency power supplies are configured as power intelligent agents to form a decentralized power intelligent agent network, and a two-layer data ledger containing an identity chain and a state chain is constructed. The identity chain is used to record the identity information and historical reputation value of each power intelligent agent, and the state chain is used to record the dynamic state information of the power intelligent agent in real time. Obtain energy demand information and generate dynamic task contracts containing task objectives and incentive weights based on the energy demand information; The power agent obtains global state information from the state chain and negotiates the dynamic task contract by combining it with locally perceived energy demand information, generating a negotiation result that includes role allocation and deployment location. A dynamic energy potential field is constructed based on the energy demand information and the deployment location in the negotiation results; The power agent plans its movement path based on the dynamic energy potential field. During the movement, the predicted trajectory and real-time position of the power agent are updated to the state chain as new dynamic state information, and dynamic path correction is performed based on the information in the state chain.

2. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The construction of a two-layer data ledger comprising an identity chain and a state chain includes: For each power agent, generate identity information containing a unique identifier and performance parameters, obtain its initial historical reputation value, and write the identity information and the historical reputation value into the identity chain; Get the power level, location and operating status of each power agent to form dynamic state information; A consensus mechanism is used to verify the consistency of the dynamic state information, and the verified dynamic state information is written into the state chain to form global state information; The identity chain and the state chain are encapsulated to construct a two-layer data ledger.

3. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The generation of a dynamic task contract containing task objectives and incentive weights includes: Collect and analyze local energy demand data, and identify demand hotspots from the energy demand data; Based on the coverage and power requirements of the aforementioned hotspot areas, generate the task target code; Incentive weights are calculated based on the importance and urgency of the task target code, and the task target code is associated with the incentive weights to form the dynamic task contract.

4. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The generated negotiation results, which include role assignments and deployment locations, include: The power agent acquires the dynamic task contract and the global state information; Each power agent calculates its bidding score by combining its own dynamic state information and the incentive weight of the dynamic task contract. A group consensus algorithm is executed among all power agents based on the bidding scores to determine a unique winning agent, and the role and corresponding deployment location of the winning agent are used as the negotiation result.

5. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The construction of the dynamic energy potential field includes: Based on the spatial distribution of the energy demand information, the initial potential energy value of each region in the preset map grid is calculated. The virtual potential field gradient is calculated based on the initial potential energy value; Based on the deployment location in the negotiation results, a local potential energy increment is introduced in the corresponding area to adjust the initial potential energy value, thereby forming the dynamic energy potential field.

6. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The planned movement path includes: The potential field gradient direction at the current position is calculated based on the dynamic energy potential field. An initial path is generated based on the potential field gradient direction and the target deployment location; The system acquires local obstacle information on the real-time travel path using preset sensors, and optimizes the initial path based on this local obstacle information to generate the final travel path.

7. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The dynamic path correction includes: The power agent monitors its predicted trajectory and the predicted trajectories recorded by other power agents on the state chain to identify potential path conflicts. After identifying the potential path conflicts, a path correction contract is generated; The power agent involved in the potential path conflict negotiates the path correction contract locally, generates a correction result, and adjusts its own movement path according to the correction result.

8. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The method further includes: After the power agent completes the task, the task completion score is calculated based on the behavioral data recorded in the state chain. The task completion score is used to update the historical reputation value of the power agent in the identity chain; The incentive weights are modified based on the updated historical reputation values.

9. The emergency power intelligent scheduling and path planning method according to claim 1, characterized in that, The method further includes: By monitoring the state chain, it can be determined whether there are any abnormal offline intelligent agents that have not updated their dynamic state information for a predetermined period of time. After determining the existence of the abnormal offline agent, obtain the unfinished dynamic task contract that it is currently executing; The incomplete dynamic task contract is decomposed into a new dynamic task contract and a new round of negotiation is triggered to achieve automatic task redistribution.

10. An emergency power intelligent scheduling and path planning system, applied to the emergency power intelligent scheduling and path planning method as described in any one of claims 1-9, characterized in that, The system includes: The power agent configuration module is used to configure multiple emergency power supplies as power agents to form a decentralized power agent network and to build a two-layer data ledger containing an identity chain and a state chain. The two-layer data ledger management module is used to acquire energy demand information and generate dynamic task contracts containing task objectives and incentive weights based on the energy demand information. The dynamic task contract generation module is used to obtain global state information from the state chain through the power agent, and negotiate the dynamic task contract in combination with the locally perceived energy demand information to generate a negotiation result that includes role allocation and deployment location. The group negotiation decision-making module is used to construct a dynamic energy potential field based on the energy demand information and the deployment location in the negotiation results. The dynamic potential field modeling module is used to plan the movement path of the power intelligent agent based on the dynamic energy potential field. The path planning and correction module is used to update the state chain with the predicted trajectory and real-time position of the power agent as new dynamic state information during the movement process, and to perform dynamic path correction based on the information in the state chain.

Images