Conference room distributed central control intelligent scheduling system and method based on load balancing

Abstract

The invention belongs to the technical field of central control systems, relates to a conference room distributed central control intelligent scheduling system and method based on load balancing, and aims at solving the problems that a traditional scheduling model is low in load evaluation accuracy and unbalanced in task distribution. According to the system, central control units receive tasks / execute the tasks, and a plurality of central control units form a distributed cluster; the load calculation and storage module determines the load value of each central control unit and stores the load value in a hash table; the local decision module determines whether the task is executed by the current central control unit or not, and if the current load is not met, the task is transferred to the leader central control unit; and the cluster management module elects a leader central control unit, and the leader central control unit determines the central control unit for executing the task according to the hash table. According to the load evaluation method, multi-index calculation and hash table storage are fused, scheduling is carried out based on local hash table decision and a Raft algorithm, evaluation is accurate, and the load balance of the central control system is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of central control systems, and in particular relates to a distributed central control intelligent scheduling system and method for conference rooms based on load balancing. Background Art

[0002] In the field of central control systems, traditional scheduling methods have long dominated. Its scheduling models mainly include centralized fixed allocation scheduling models, simple polling scheduling models, and scheduling models based on fixed priorities. The centralized fixed allocation scheduling model allocates tasks to each central control unit according to pre-set fixed rules. For example, central control unit A is responsible for display device-related tasks, and central control unit B is responsible for air-conditioning-related tasks. The simple polling scheduling model saves the list data of all central control units through the task scheduling module and allocates tasks to the central control units in sequence. The scheduling model based on fixed priorities sets a fixed priority order for different types of tasks and central control units, and assigns tasks according to this order. These traditional scheduling models all make scheduling decisions based on static parameters preset in the central control unit. They are relatively simple to implement and manage, and can meet the basic needs of some relatively simple scenarios.

[0003] However, with the continuous development of technology and the increasing complexity of application scenarios, the drawbacks of the traditional central control system scheduling model have gradually become apparent. On the one hand, it is difficult for the traditional model to accurately and in real time evaluate and monitor the load conditions of each central control unit, resulting in a lack of rationality in task allocation; it is easy for some central control units to delay task processing due to excessive load, while other central control units have idle resources. This imbalance greatly affects the overall operating efficiency of the equipment. On the other hand, in the distributed task scheduling process, there is a lack of an effective overall coordination mechanism to ensure load balancing at the distributed central control system level, resulting in a decline in the overall system performance and stability, making it difficult to meet the stringent requirements of modern conference rooms for equipment control in terms of efficiency, smoothness and reliability. Therefore, there is an urgent need for a new central control system scheduling technology that can solve the above problems. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, namely, the low load assessment accuracy, insufficient scheduling coordination, and unbalanced task allocation of traditional central control system scheduling models, the first aspect of the present invention proposes a distributed central control intelligent scheduling system for conference rooms based on load balancing to achieve efficient task allocation and migration. The system includes: A central control unit is configured to receive task instructions and send them to its corresponding local decision module; wherein multiple central control units automatically form a distributed central control unit cluster based on the Raft algorithm; A load calculation and storage module is configured to determine the overall load value of each central control unit based on a preset load index, store it in a hash table, and regularly update the load information; if the load index changes during task execution, the corresponding information in the hash table is synchronously updated; The local decision module is configured to query the hash table to obtain the load of the central control unit that receives the task instruction. If the load meets the preset execution condition, the current central control unit directly executes the task instruction; otherwise, the task instruction is sent to the leader central control unit; The cluster management module is configured such that, when the cluster is started, each central control unit selects and determines a leader central control unit based on the Raft algorithm. Each central control unit regularly reports its own load information to the leader central control unit, which then integrates and synchronizes it to all central control units. After receiving the task instruction, the leader central control unit performs global scheduling based on the full load information in the hash table, determines the optimal central control unit to undertake the task instruction, and instructs it to execute the task instruction. The instructions for executing the task are: The central control unit adds the task instructions to be executed to its local multi-level priority task queue according to the priority level and executes them.

[0005] In some preferred embodiments, the overall load value of each central control unit is determined based on a preset load index by: For each load indicator, we comprehensively scan the extreme values ​​of that indicator in all central control units, use a standardized calculation formula to convert the original indicator value into a normalized standard value, and then use a weighted summation algorithm to calculate the overall load value of each central control unit; The preset load indicators include CPU usage, memory occupancy, current task quantity, task processing queue length, and bandwidth utilization for communicating with the device.

[0006] In some preferred embodiments, the overall load value of each central control unit is stored in a hash table by: The device ID of the central control unit is used as the primary key of the hash table, and the corresponding load information is used as the storage value.

[0007] In some preferred implementations, the execution conditions are that the load is within a reasonable range and there are sufficient local resources, specifically including the following: The load value of the central control unit is lower than M%, and each preset load indicator meets the requirements of the task to be executed; and among the tasks being executed by the central control unit, resources have been reserved for high-priority tasks and will not affect the execution of high-priority tasks after accepting the tasks to be executed; for medium and low priority tasks, the load fluctuation within the set time period after accepting the tasks to be executed is less than the set fluctuation amplitude range.

[0008] In some preferred embodiments, global scheduling is performed based on the full load information in the hash table, including task migration scheduling and task allocation scheduling; The task migration scheduling method is as follows: If a central control unit triggers the task migration function, the leader central control unit queries the full load information in the hash table, filters out the target central control unit whose load meets the migration conditions and has the ability to process the migration task, and sends the relevant information of the migration task to the target central control unit. The target central control unit executes the task and sends the migration progress back to the leader central control unit. The relevant information includes task type, execution parameters and current execution progress; The task allocation and scheduling method is as follows: When receiving the task instruction, the leader central control unit queries the full load information in the hash table, calculates the task allocation coefficient of each central control unit to determine the optimal central control unit, and sends the task instruction to be executed to the optimal central control unit.

[0009] In some preferred implementations, the task migration function MigerationTrigger i for: Among them, HighLoadThreshold is the high load threshold, LowLoadThreshold is the low load threshold, Load i is the overall load value of the i-th central control unit, i = 1, 2, ... N; When MigerationTrigger i =1, it means that the load of the central control unit is too high and the task needs to be migrated out; when MigerationTrigger i = -1, it means that the load of the central control unit is too low, and the migration conditions are met, and it can receive tasks migrated from other central control units; when MigerationTrigger i =0, indicating that the central control unit load is within the normal range and no task migration operation is required.

[0010] In some preferred embodiments, the task allocation coefficient Allocation i,T for: Among them, Load i is the overall load value of the i-th central control unit; Resource i,TRepresents the resources required by the i-th central control unit to process task T, i = 1, 2, ...N.

[0011] In some preferred implementations, when determining the optimal central control unit to undertake the task, the priority of the task, the current idle status of resources of each central control unit, and the intrinsic correlation between the task and the devices controlled by each central control unit are comprehensively considered.

[0012] A method for intelligent scheduling of distributed central control in conference rooms based on load balancing, the method comprising the following steps: S1. Build a distributed central control unit cluster based on the Raft algorithm, elect a leader central control unit, and each central control unit regularly reports its own load information to the leader central control unit, which then integrates and synchronizes it to all central control units. S2. Receive task instructions issued by the user; S3. Determine whether the load of the current central control unit meets the execution conditions. If so, the current central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table; if not, send the task instruction to the leader central control unit for global scheduling; S4. The leader central control unit determines and forwards the task to the optimal central control unit based on the full load information in the hash table. The central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table.

[0013] In some preferred embodiments, in S1, if the leader central control unit detects that there is a central control unit triggering a task migration function, task allocation and scheduling are performed based on the full load information stored in the hash table to balance the overall system load.

[0014] Beneficial effects of the present invention: The present invention integrates a load assessment system that combines multi-index weighted calculation with hash table storage, accurately quantifies the load of central control units, efficiently stores and updates load information, and accurately assesses the load of each central control unit. Furthermore, a task scheduling mechanism based on local hash table decision-making and coordinated with the Raft algorithm ensures that the load of each central control unit is balanced, greatly avoiding overloading of some central control units due to excessive task loads and preventing idle resources in other central control units. This significantly improves the load balancing of the entire central control system, thereby greatly improving equipment operating efficiency. The system uses a design that combines multi-priority queues with a thread pool architecture and incorporates a dynamic adjustment mechanism. Tasks of different priorities are orderly assigned to corresponding queues. The thread pool dynamically adjusts the number of threads to process tasks based on system load and task priority, significantly reducing task response delays and enhancing task processing efficiency. Dynamically adjust task priorities based on conference and system status, reserve key resources, and optimize task scheduling for cache reuse. Dynamically adjust task priorities in real time based on conference progress and system status to improve system performance and response speed, optimize resource utilization, ensure efficient, smooth, and reliable device control, and ensure the smooth progress of key conference links, providing a solid guarantee for the efficient and stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 This is a flowchart of the system performing task scheduling when a new task is triggered in an embodiment of the present invention; Figure 2 This is a flowchart of performing task migration when a task migration function is triggered in an embodiment of the present invention; Figure 3 Schematic diagram of data interaction between central control units in an embodiment of the present invention; Figure 4 4 is an architectural diagram of a local multi-level priority task queue in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0017] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0018] This invention realizes efficient task allocation and migration through a combination of a local decision-making mechanism and a global scheduling strategy based on the Raft algorithm, achieving precise load balancing. At the same time, it uses the Raft algorithm to ensure the consistency of load information and task scheduling status in the cluster, comprehensively improving the performance, stability and reliability of the system, and providing solid technical support for the intelligent control of conference room equipment.

[0019] In order to more clearly explain the distributed central control intelligent scheduling system for conference rooms based on load balancing of the present invention, Figure 1 Each module in the embodiment of the present invention is described in detail. The system includes:

[0020] The first aspect of the present invention proposes a distributed central control intelligent scheduling system for conference rooms based on load balancing to achieve efficient allocation and migration of tasks. The system includes: A central control unit is configured to receive task instructions, wherein a plurality of the central control units form a distributed central control unit cluster based on the Raft algorithm; and is further configured to execute the assigned task instructions after local decision-making, and add the task instructions to a local multi-level priority task queue according to the priority level and execute them; A load calculation and storage module is configured to determine the overall load value of each central control unit based on a preset load index, store the value in a hash table, and regularly update the load information; if the load index changes during task execution, the corresponding information in the hash table is synchronously updated for query and call by each central control unit; A local decision module is configured to query the hash table to obtain the load of the central control unit that receives the task instruction. If the current load meets the execution condition, the current central control unit directly executes the task instruction; otherwise, the task instruction is sent to the leader central control unit; The cluster management module is configured so that when the cluster is started, each central control unit elects a leader central control unit based on the Raft algorithm rules. Each central control unit regularly reports its own load information to the leader central control unit, which integrates and synchronizes it to all central control units. After receiving the task instruction, the leader central control unit performs global scheduling based on the full load information in the hash table, determines the optimal central control unit to undertake the task instruction, and instructs it to execute the task instruction.

[0021] Preferably, each central control unit has the following multiple working modes: As the local central control unit that receives task instructions, when the local decision module determines that the load is met, it directly puts the received task instructions into the local multi-level priority task queue and executes the task instructions; As the elected leader central control unit, it receives the transferred task instructions, performs global scheduling of tasks based on the full load information in the hash table, accurately determines the optimal central control unit to take over through scheduling, and forwards the task instructions to the optimal central control unit. As the optimal central control unit selected, it receives the task instructions forwarded by the leader central control unit, places the task instructions in the local multi-level priority task queue according to the priority level, and executes the task instructions.

[0022] Preferably, the overall load value of each central control unit is determined based on the preset load index, and the method is as follows: For each load indicator, we comprehensively scan the extreme values ​​of that indicator in all central control units, use a standardized calculation formula to convert the original indicator value into a normalized standard value, and then use a weighted summation algorithm to calculate the overall load value of each central control unit; The preset load indicators include CPU usage, memory occupancy, number of current tasks, task processing queue length, and bandwidth utilization for communicating with the device.

[0023] Furthermore, in this embodiment, for the i-th indicator X of the j-th central control unit ji , and its standardized index value is: Then, the weighted summation algorithm is used to accurately calculate the overall load value of each central control unit. The summation formula is: Load j =∑w i ×y ji ; Among them, w i is the weight of each indicator and ∑w i =1.

[0024] Furthermore, based on the degree of impact of each indicator on system performance, a reasonable weight range is set for each indicator. In this embodiment, the CPU usage weight is set between 30% and 50%, and the memory usage weight is set between 20% and 30%. This ensures that the load calculation can accurately reflect the actual workload of the central control unit.

[0025] Preferably, the overall load value of each central control unit is stored in a hash table in the following manner: The device ID of the central control unit is used as the primary key of the hash table, and the corresponding load information is used as the storage value. Each central control unit actively updates its own load information according to the preset time period and stores it in the hash table. At the same time, during the task execution process, once the load indicator changes due to the addition or completion of tasks or other factors, the corresponding information in the hash table is updated immediately and synchronously.

[0026] As an option, in this embodiment, the preset time period is 1 minute.

[0027] In some preferred implementations, the execution conditions are that the load is within a reasonable range and there are sufficient local resources, specifically including the following: The load value of the central control unit is lower than M%, and in this embodiment, M=60; each preset load indicator shows that resources are sufficient and meet the requirements of the tasks to be executed; and among the tasks being executed by the central control unit, sufficient key resources have been reserved for high-priority tasks to ensure their smooth execution, that is, resources have been reserved and will not affect the execution of high-priority tasks after accepting the tasks to be executed; for medium and low priority tasks, accepting the tasks to be executed will not cause a sharp increase in load, that is, the load fluctuation in the set time period after accepting the tasks to be executed is less than the set fluctuation amplitude range.

[0028] Specifically, the priority level is determined according to a pre-set task priority determination system. For example, tasks involving equipment operation in key aspects of a conference are set to a high priority.

[0029] The local multi-level priority task queue, such as Figure 4 As shown in the figure, a high, medium and low priority task queue architecture is designed within a single central control unit. The high-priority task queue is dedicated to handling emergency control tasks for key equipment during a meeting (such as projectors and microphones in use), ensuring that such tasks that have a critical impact on the progress of the meeting and have extremely high timeliness requirements can be responded to and processed immediately; the medium-priority task queue is mainly responsible for routine equipment control tasks, such as flexible adjustment of lighting brightness, precise setting of air-conditioning temperature, etc.; the low-priority task queue focuses on the processing of non-emergency tasks, covering periodic or background tasks such as equipment inspection and data backup. Through this refined task classification management mechanism, orderly diversion of tasks and preliminary load balancing deployment within the central control unit are achieved.

[0030] Preferably, the Raft algorithm is introduced to build a distributed central control unit cluster. When the cluster starts, each central control unit participates in the election process of the leader central control unit according to the Raft algorithm rules; through multiple rounds of heartbeat detection, voting and other mechanisms, a leader central control unit is elected. The leader central control unit assumes the core coordination and decision-making responsibilities in the entire distributed system and becomes the key hub for system task scheduling and load balancing.

[0031] Furthermore, in this embodiment, each central control unit regularly uploads updated data about its own load information to the leader central control unit. The leader central control unit is responsible for collecting and integrating this information and broadcasting it to other central control units through the log replication mechanism of the Raft algorithm. Other central control units receive and apply this log information in a strictly identical order, ensuring that across the entire distributed central control system, each central control unit maintains a highly consistent understanding of the load information of each central control unit within the system. This effectively avoids task scheduling conflicts or incorrect decisions caused by inconsistent information, laying a solid foundation for the stability and reliability of task scheduling.

[0032] Preferably, global scheduling is performed based on the full load information in the hash table, including task migration scheduling and task allocation scheduling; When it is detected that there is a central control unit triggering the task migration function, the leader central control unit performs task migration scheduling in the following way: If a central control unit triggers the task migration function, the leader central control unit queries the full load information in the hash table, selects the target central control unit with suitable load and the ability to handle the migration task, and sends the relevant information of the migration task (including task type, execution parameters, current execution progress, etc.) to the target central control unit. The target central control unit executes the task and returns the migration progress to the leader central control unit. The relevant information includes task type, execution parameters and current execution progress; When the local central control unit determines that it cannot properly handle the task based on the local decision rule, the leader central control unit performs task allocation and scheduling in the following way: When receiving the task instruction, the leader central control unit queries the full load information in the hash table, calculates the task allocation coefficient of each central control unit to determine the optimal central control unit, and sends the task instruction to be executed to the optimal central control unit.

[0033] Preferably, the task migration function MigerationTrigger i for: Among them, HighLoadThreshold is the high load threshold, LowLoadThreshold is the low load threshold, Load i is the overall load value of the i-th central control unit, i = 1, 2, ... N; When MigerationTrigger i =1, it means that the load of the central control unit is too high and the task needs to be migrated out; when MigerationTrigger i = -1, indicating that the central control unit load is too low and can accept tasks migrated from other central control units; when MigerationTrigger i =0, indicating that the central control unit load is within the normal range and no task migration operation is required.

[0034] Through refined coordination and management, tasks can be flexibly deployed among distributed central control units and load balancing can be optimized and reshaped, effectively resolving system performance bottlenecks that may be caused by local load imbalances.

[0035] Preferably, the task allocation coefficient Allocation i,T for: Among them, Load i is the overall load value of the i-th central control unit; Resource i,T Indicates the resources required by the i-th central control unit to process task T, i = 1, 2, ... N. i Small) and have more resources required to process tasks (Resource i,T Larger) central control unit, its allocation coefficient Allocation i,T will be larger, and thus more likely to be assigned to task T.

[0036] Optimally, when determining the optimal central control unit to undertake the task, it is necessary to comprehensively consider the task priority, the current resource idleness of each central control unit, and the inherent correlation between the task and the equipment controlled by each central control unit. For example, for a task involving group control of lighting equipment in a specific area, the leader central control unit will deeply analyze the connection topology relationship between each central control unit and the lighting equipment in that area, as well as its current load situation, and ultimately select the central control unit with the lightest load and the closest connection to the lighting equipment in that area as the main body of task execution. This ensures that the task can be efficiently processed in an optimal resource adaptation environment, while effectively maintaining the dynamic stability of the overall load balancing of the system.

[0037] It should be noted that the load-balancing-based distributed central control intelligent scheduling system for conference rooms provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps and are not considered to be improper limitations of the present invention.

[0038] A second embodiment of the present invention provides a method for intelligently scheduling a conference room's distributed central control system based on load balancing, the method comprising: S1. Build a distributed central control unit cluster based on the Raft algorithm, elect a leader central control unit, and each central control unit regularly reports its own load information to the leader central control unit, which collects and integrates the information and synchronizes it to all central control units. S2. Receive task instructions issued by the user; S3. Determine whether the load of the current central control unit meets the execution conditions. If so, the current central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table; if not, send the task instruction to the leader central control unit for global scheduling; S4. The leader central control unit determines and forwards the task to the optimal central control unit based on the full load information in the hash table. The central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table.

[0039] Preferably, in S1, when the leader central control unit detects that there is a central control unit triggering a task migration function, task allocation and scheduling are performed according to the full load information stored in the hash table to balance the overall system load.

[0040] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the above-described method can refer to the corresponding process in the aforementioned system embodiment and will not be repeated here.

[0041] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art will understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0042] An electronic device according to a third embodiment of the present invention includes: at least one processor; and a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned conference room distributed central control intelligent scheduling method based on load balancing.

[0043] A fourth embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned conference room distributed central control intelligent scheduling method based on load balancing.

[0044] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes and related instructions of the electronic device and computer-readable storage medium described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0045] Those skilled in the art should be able to appreciate that, in conjunction with the modules and method steps of each example described in the embodiments disclosed herein, it is possible to implement them with electronic hardware, computer software, or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0046] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0047] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0048] The terms "first", "second", etc. are used to distinguish similar objects, rather than to describe or indicate a particular order or sequence.

[0049] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0050] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A distributed central control intelligent scheduling system for conference rooms based on load balancing, characterized in that: The system comprises: A central control unit is configured to receive task instructions and send them to its corresponding local decision module; wherein multiple central control units automatically form a distributed central control unit cluster based on the Raft algorithm; A load calculation and storage module is configured to determine the overall load value of each central control unit based on a preset load index, store it in a hash table, and regularly update the load information; if the load index changes during task execution, the corresponding information in the hash table is synchronously updated; The local decision module is configured to query the hash table to obtain the load of the central control unit that receives the task instruction. If the load meets the preset execution condition, the current central control unit directly executes the task instruction; otherwise, the task instruction is sent to the leader central control unit; The cluster management module is configured such that, when the cluster is started, each central control unit selects and determines a leader central control unit based on the Raft algorithm. Each central control unit regularly reports its own load information to the leader central control unit, which then integrates and synchronizes it to all central control units. After receiving the task instruction, the leader central control unit performs global scheduling based on the full load information in the hash table, determines the optimal central control unit to undertake the task instruction, and instructs it to execute the task instruction. The instructions for executing the task are: The central control unit adds the task instructions to be executed to its local multi-level priority task queue according to the priority level and executes them.

2. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 1 is characterized in that: The overall load value of each central control unit is determined based on the preset load index. The method is as follows: For each load indicator, we comprehensively scan all central control units for the extreme values ​​of that load indicator, use a standardized calculation formula to convert the original indicator value into a normalized standard value, and then use a weighted summation algorithm to calculate the overall load value of each central control unit; The preset load indicators include CPU usage, memory occupancy, current task quantity, task processing queue length, and bandwidth utilization for communicating with the device.

3. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 2 is characterized in that: The overall load value of each central control unit is stored in the hash table as follows: The device ID of the central control unit is used as the primary key of the hash table, and the corresponding load information is used as the storage value.

4. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 2 is characterized in that: The execution conditions are that the load is within a reasonable range and there are sufficient local resources, specifically including the following: The load value of the central control unit is lower than M%, and each preset load indicator meets the requirements of the task to be executed; and among the tasks being executed by the central control unit, resources have been reserved for high-priority tasks and will not affect the execution of high-priority tasks after accepting the tasks to be executed; for medium and low priority tasks, the load fluctuation within the set time period after accepting the tasks to be executed is less than the set fluctuation amplitude range.

5. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 1 is characterized in that: Perform global scheduling based on the full load information in the hash table, including task migration scheduling and task allocation scheduling; The task migration scheduling method is as follows: If a central control unit triggers the task migration function, the leader central control unit queries the full load information in the hash table, filters out the target central control unit whose load meets the migration conditions and has the ability to process the migration task, and sends the relevant information of the migration task to the target central control unit. The target central control unit executes the task and sends the migration progress back to the leader central control unit. The relevant information includes task type, execution parameters and current execution progress; The task allocation and scheduling method is as follows: When receiving the task instruction, the leader central control unit queries the full load information in the hash table, calculates the task allocation coefficient of each central control unit to determine the optimal central control unit, and sends the task instruction to be executed to the optimal central control unit.

6. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 5 is characterized in that: The task migration function MigerationTrigger i for: Among them, HighLoadThreshold is the high load threshold, LowLoadThreshold is the low load threshold, Load i is the overall load value of the i-th central control unit, i = 1, 2, ... N; When MigerationTrigger i =1, it means that the load of the central control unit is too high and the task needs to be migrated out; when MigerationTrigger i = -1, it means that the load of the central control unit is too low, and the migration conditions are met, and it can receive tasks migrated from other central control units; when MigerationTrigger i =0, indicating that the central control unit load is within the normal range and no task migration operation is required.

7. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 5 is characterized in that: The task allocation coefficient Allocation i,T for: Among them, Load i is the overall load value of the i-th central control unit; Resource i,T Represents the resources required by the i-th central control unit to process task T, i = 1, 2, ...N.

8. The distributed central control intelligent scheduling system for conference rooms based on load balancing according to claim 1 is characterized in that: When determining the optimal central control unit to undertake the task, the priority of the task, the current idle status of the resources of each central control unit, and the intrinsic correlation between the task and the equipment controlled by each central control unit are comprehensively considered.

9. A method for intelligent scheduling of distributed central control systems for conference rooms based on load balancing, according to the system for intelligent scheduling of distributed central control systems for conference rooms based on load balancing according to any one of claims 1 to 8, the method comprising the following steps: S1. Build a distributed central control unit cluster based on the Raft algorithm, elect a leader central control unit, and each central control unit regularly reports its own load information to the leader central control unit, which then integrates and synchronizes it to all central control units. S2. Receive task instructions issued by the user; S3. Determine whether the load of the current central control unit meets the execution conditions. If so, the current central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table; if not, send the task instruction to the leader central control unit for global scheduling; S4. The leader central control unit determines and forwards the task to the optimal central control unit based on the full load information in the hash table. The central control unit adds the task instruction to the local multi-level priority task queue according to the priority level and executes it, and synchronously updates the corresponding information in the hash table.

10. The method for intelligent scheduling of conference room distributed central control based on load balancing according to claim 9 is characterized in that: In S1, if the leader central control unit detects that there is a central control unit triggering a task migration function, task allocation and scheduling are performed according to the full load information stored in the hash table to balance the overall system load.

Images