Thermal management in network switch

Abstract

The invention relates to thermal management in a network switch. An apparatus includes an interface and a thermal management circuit (TMC). The interface is configured to receive a plurality of measurements of a plurality of temperatures measured in a plurality of locations of the electronic system, respectively. The TMC is configured to (a) convert the plurality of measurements into a plurality of pulse width modulation (PWM) parameters, (b) calculate one or more PWM signals based at least on the plurality of PWM parameters, and (c) control the plurality of temperatures by applying the one or more PWM signals to the one or more cooling devices.

Description

Technical Field

[0001] The present invention relates generally to electronic systems and, more particularly, to techniques for improving thermal management in network switch systems. Background Art

[0002] Various techniques are known in the art for dissipating heat generated in switch systems. Summary of the invention

[0003] Embodiments of the invention described herein provide a device including an interface and a thermal management circuit (TMC). The interface is configured to receive a plurality of measurements of a plurality of temperatures measured in a plurality of locations of an electronic system, respectively. The TMC is configured to: (a) convert the plurality of measurements into a plurality of pulse width modulation (PWM) parameters, (b) calculate one or more PWM signals based at least on the plurality of PWM parameters, and (c) control the plurality of temperatures by applying the one or more PWM signals to one or more cooling devices.

[0004] In some embodiments, the TMC is configured to: (i) select a PWM parameter from a plurality of PWM parameters, such as a maximum PWM parameter or a PWM parameter that satisfies a predetermined condition, and (ii) apply the selected PWM parameter to all cooling devices. In other embodiments, the TMC is configured to select a list of two or more components located at two or more locations, and the device includes two or more temperature sensors respectively coupled to the components, and the temperature sensors are configured to respectively perform temperature measurements in the components in the list. In still other embodiments, the interface is configured to receive an error signal indicating an error in at least one of: (i) one or more cooling devices, and (ii) one or more temperature sensors, and the TMC is configured to adjust at least one PWM signal in response to the error.

[0005] In some embodiments, the plurality of temperature sensors include a first temperature sensor and a second temperature sensor, respectively used to perform a first measurement and a second measurement in the plurality of measurements, and the TMC includes a controller configured to define: (i) for the first temperature sensor, a first frequency of the first measurement, and (ii) for the second temperature sensor, a second frequency of the second measurement, the second frequency being different from the first frequency. In other embodiments, the TMC includes a controller configured to calculate a ratio between a plurality of PWM parameters and a plurality of parameters of one or more cooling devices. In other embodiments, at least one of the cooling devices includes a fan, at least one of the plurality of parameters includes a rotational speed of the fan, and the controller is configured to calculate a ratio between the rotational speed of the fan and a corresponding PWM parameter in the plurality of PWM parameters.

[0006] In some embodiments, the device includes (i) multiple fans that are respectively controlled to operate at multiple speeds, (ii) multiple components located at at least some of the multiple locations, and (iii) a power supply unit (PSU) for supplying power to at least some of the multiple components, the PSU includes a PSU fan, and the TMC is configured to set a given speed of the PSU fan to be equal to or greater than a maximum speed among the multiple speeds.

[0007] In other embodiments, the controller is configured to control a rotation direction of the fan, the plurality of measurements include two or more given measurements indicative of ambient temperatures of the electronic system, and the controller is configured to determine the rotation direction of the fan based on a minimum ambient temperature among the ambient temperatures.

[0008] In yet other embodiments, at least one cooling device includes a pump configured to flow a cooling fluid to cool at least one of a plurality of locations, at least one of a plurality of parameters includes a flow rate of the cooling fluid, and the controller is configured to calculate a ratio between the flow rate of the cooling fluid and a corresponding PWM parameter of a plurality of PWM parameters.

[0009] According to an embodiment of the present invention, a method is also provided, comprising: receiving a plurality of measurement values ​​of a plurality of temperatures measured in a plurality of locations of an electronic system, respectively, converting the plurality of measurement values ​​into a plurality of pulse width modulation (PWM) parameters, calculating one or more PWM signals based at least on the plurality of PWM parameters, and controlling the plurality of temperatures by applying the one or more PWM signals to one or more cooling devices.

[0010] The present invention will be more fully understood from the following detailed description of embodiments thereof in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic diagram of a switch system for a communication network according to an embodiment of the present invention;

[0012] Figure 2 is a schematic diagram showing monitoring and control according to an embodiment of the present invention Figure 1 A block diagram of the temperatures of components in a switch system; and

[0013] Figure 3 is a schematic diagram showing monitoring and control according to an embodiment of the present invention Figure 1 A flow chart of a method of controlling the temperature of a component in a switch system. DETAILED DESCRIPTION

[0014] Overview

[0015] Electronic systems, such as switch systems (also referred to herein as network switches) of a communication network, typically generate heat when operating. For example, each switch system may include multiple types of electronic devices, such as, but not limited to, application specific integrated circuits (ASICs), processors and / or controllers, and memory storage devices. During operation of the switch system, the electronic devices generate heat, which may degrade the functionality of the system and, in severe cases, may burn out one or more components of the system. Various heat dissipation solutions have been developed for such systems, but each solution uses different hardware and software techniques, and there is a need to implement a common thermal management solution in one or more communication networks having different types of switch systems.

[0016] Embodiments of the invention described below provide techniques for improving heat dissipation in electronic systems, such as various types of switch systems used in communications networks.

[0017] In some embodiments, the switch system includes multiple devices, such as but not limited to (i) one or more switches implemented in one or more ASICs, (ii) one or more data processing units (DPUs), (iii) processors, (iv) electro-optical transceivers, (v) power supply units, (vi) cooling devices, such as fans and fluid pumps, and (vii) one or more drivers configured to drive signals to the cooling devices. The switch system also includes temperature sensors located at predefined locations (also referred to herein as hot zones) within the switch system. It is noteworthy that at least some of the devices are located at predefined locations and at least some of the temperature sensors are embedded in the devices. For example, one or more temperature sensors are embedded in the ASIC. Therefore, the temperature sensors are configured to generate signals indicating the temperature at the corresponding predefined locations.

[0018] In some embodiments, the switch system includes a device for controlling the temperature at some or all of the predefined locations (e.g., hot zones). The device includes an interface configured to receive temperature measurements from various temperature sensors. The device also includes a controller, for example, implemented in the processor described above, or implemented as a separate controller device. The controller is configured to convert a plurality of temperature measurements at each predefined location into a plurality of pulse width modulation (PWM) parameters, each parameter being associated with a corresponding predefined location.

[0019] It is noted that the PWM parameters are measured in percentages and may be different from each other. For example, the first PWM parameter and the second PWM parameter are associated with an ASIC and a processor located at different locations and have PWM parameters of approximately 70% and 50%, respectively, and all other PWM parameters have values ​​less than approximately 50%.

[0020] In some embodiments, the controller is configured to calculate one or more PWM signals based on the PWM parameters. In one example, the controller can select a maximum PWM parameter (e.g., 70%) among all PWM parameters to calculate the PWM signal. In another example, the controller can select two or more PWM parameters for calculating two or more PWM signals.

[0021] In some embodiments, one or more drivers are configured to drive one or more PWM signals calculated by the controller to one or more cooling devices, respectively.

[0022] In some embodiments, in the event of an error in one or more components of the switch system (e.g., a temperature sensor and / or a cooling device), the controller is configured to adjust at least one PWM signal to compensate for the error or increase the cooling level to obtain thermally safe operation of the switch system. Figures 1 to 3 Described in more detail in .

[0023] The disclosed technology improves the availability and performance of communication systems by optimizing the thermal performance of such systems. In addition, the disclosed technology provides a unified temperature control flow in all types of switch systems, regardless of the type of software and / or firmware that can be used to manage thermal control of the corresponding type of switch system.

[0024] System Description

[0025] Figure 1 1 is a schematic diagram of an electronic system according to an embodiment of the present invention, in this example, a switch system 11 used in a communication network. For simplicity, the switch system 11 is also referred to as system 11 herein.

[0026] In some embodiments, the system 11 includes a front panel 12 having a receptacle 14 connected between electro-optical transceivers (EOTRs) 10, the receptacle 14 being configured to be plugged into and unplugged from a connector 13. In this example, the connector 13 includes a quad small form-factor pluggable (QSFP) connector. In some embodiments, each EOTR 10 includes a temperature sensor 23 configured to generate a signal indicating a temperature measured in the EOTR 10 and a time when the EOTR 10 is plugged into a given connector 13.

[0027] In some embodiments, system 11 includes a housing 15 for enclosing components described below, and circuit boards (CB) 31 and 32 having a plurality of devices and other components mounted thereon and described in detail below.

[0028] In some embodiments, the system 11 includes a network switch device, which is implemented in an application specific integrated circuit (ASIC) 20 in this example, and the ASIC 20 is mounted on the CB 31. It is worth noting that the ASIC 20 generates heat when in operation. In some embodiments, the system 11 includes a temperature sensor 24, which is embedded in the ASIC 20 (but can be coupled to the ASIC 20 instead). In some embodiments, the sensor 24 can be implemented as a plurality of temperature sensors implemented at several corresponding locations on the ASIC 20. These temperature sensors are configured to generate a signal indicating the temperature measured at one or more locations on the ASIC 20.

[0029] In some embodiments, system 11 includes a processor 44, such as a suitable type of central processing unit (CPU) or any other suitable type of processing unit, and a temperature sensor 26 coupled to or embedded within processor 44. Sensor 26 is configured to generate a signal indicative of a temperature measured at one or more locations within processor 44.

[0030] In some embodiments, the system 11 includes additional components, such as (i) a power supply regulator (DCDC) mounted on the other side of the CB 31 and therefore not shown, the DCDC being configured to convert a first direct current (DC) into a second DC, (ii) a temperature sensor 25 being configured to generate signals indicating temperatures at multiple locations of the DCDC, (iii) an interface 55 being configured to exchange signals between the processor 44 and other entities of the system 11, as will be described in detail below, (iv) a memory device, in this example, a double data rate synchronous dynamic random access memory (DDR SDRAM), referred to herein as DDR 21, and (v) a temperature sensor 27 being coupled to or embedded within the DDR 21 and configured to generate signals indicating temperatures measured at one or more locations on the DDR 21.

[0031] In some embodiments, system 11 includes one or more heat sinks and thermal interface materials (TIMs) disposed over at least some of the heat generating devices (eg, ASIC 20, processor 44, and DDR 21) to increase the rate at which heat generated by these devices is dissipated.

[0032] In some embodiments, system 11 includes a plurality of cooling devices, in this example, fans 16, 17, 18, and 19 configured to rotate at a controllable speed, such as measured in revolutions per minute (RPM), so as to blow air (into or out of system 11) to cool hot areas of system 11. The operation of fans 16-19 is controlled, as will be described in detail below.

[0033] In the context of the present disclosure and claims, the term "thermal zone" and grammatical variations thereof refer to a location within the system 11 whose temperature is monitored using signals received from the temperature sensors described above.

[0034] In some embodiments, the system 11 includes one or more power supply units (PSUs) 66 configured to provide power to at least some components (e.g., ASICs 20, processors 44, DDR 21, and connectors 13), and generally to all power-consuming components of the system 11. In some embodiments, the system 11 also includes one or more PSU cooling devices, in this example, PSU fans 77 (e.g., each PSU 66 has at least one PSU fan 77). The PSU fans 77 are configured to rotate at a controllable speed (e.g., measured in RPM) to cool the PSU 66. In addition, the system 11 includes one or more temperature sensors 28 (also referred to herein as ambient temperature sensors 28) configured to generate signals indicative of temperatures measured at one or more locations in the system 11. In this example, a single temperature sensor 28 is mounted on the CB 32 for monitoring the ambient temperature of the system 11, but in other embodiments, the system 11 may include any suitable number of temperature sensors 28 mounted at any suitable location within the system 11.

[0035] In some embodiments, the system 11 includes one or more drivers 33 configured to drive signals to several cooling devices of the system 11. In this example, the driver 33 is implemented in a field programmable gate array (FPGA), but in other embodiments, the driver 33 can be implemented in any other suitable type of device. The driver 33 is configured to drive signals to the fans 16-19 to blow air to control the temperature of selected components of the system 11 (e.g., connector 13, ASIC 20, processor 44, interface 55, DDR 21, driver 33, and power regulator DCDC).

[0036] In some embodiments, system 11 includes thermal management circuitry (TMC) 22, including: (i) a controller implemented in processor 44, and (ii) one or more drivers 33. In some embodiments, interface 55 is configured to receive signals from temperature sensors of system 11 indicating measurements of temperatures in a plurality of thermal zones of system 11.

[0037] As discussed above, the term "hot zone" refers to a location within the system 11 whose temperature is monitored using signals received from the temperature sensors discussed above.

[0038] In this example, interface 55 receives signals from temperature sensors 23, 24, 25, 26, 27, and 28 that indicate measured values ​​of temperatures in corresponding thermal zones of system 11. A thermal zone typically surrounds one or more temperature sensors. For example, ASIC 20 constitutes a first thermal zone surrounding temperature sensor 24, while the power regulator constitutes a second thermal zone surrounding temperature sensor 25.

[0039] In some embodiments, the controller is configured to convert the measurements received from the temperature sensors into pulse width modulation (PWM) parameters that indicate the desired speed (e.g., RPM) of the fans of the system 11. Notably, each thermal zone receives PWM parameters based on the temperature measurements. Thus, the TMC 22 acts as a thermal entity, which is defined as an entity that monitors the thermal zones (based on the temperature measurements) and controls the cooling devices (e.g., fans 16-19) of the system 11, as described herein.

[0040] In some embodiments, based on the plurality of PWM parameters, the controller is configured to calculate one or more PWM signals. For example, the controller is configured to: (i) convert a relatively low temperature (e.g., about 40° C.) measured by sensor 24 in ASIC 20 into a relatively low PWM parameter (e.g., about 30% PWM), (ii) convert a relatively high temperature (e.g., about 70° C.) measured by sensor 26 in processor 44 into a relatively high PWM parameter (e.g., about 75% PWM), and (iii) convert a temperature less than about 60° C. measured by the other temperature sensors mentioned above into a PWM parameter less than about 75%.

[0041] In some embodiments, the controller is configured to: (i) select a maximum PWM parameter among all calculated PWM parameters (approximately 75% in this example), and (ii) calculate a unified PWM signal for all fans 16-19 based on the maximum PWM parameter (75%).

[0042] In some embodiments, one or more drivers 33 are configured to apply a uniform PWM signal to all cooling devices of system 11, in this example, to fans 16-19. It is worth noting that only 75% of the relatively high PWM parameters are needed to control the temperature in processor 44, but this level of PWM parameters is applied to all fans 16-19 to alleviate overheating in the hottest thermal zone of system 11.

[0043] In an alternative embodiment, the controller is configured to calculate two or more PWM signals based on the converted PWM parameters. For example, fans 17 and 18 face processor 44, so driver 33 can: (i) apply a first PWM signal to fans 17 and 18 based on a 75% PWM parameter, and (ii) apply a second PWM signal to fans 16 and 19 based on a PWM parameter having a smaller value (e.g., approximately 65%).

[0044] In some embodiments, the controller is configured to calculate a ratio between the PWM parameter and one or more parameters of each of the fans 16-19 of the system 11. In this example, all fans 16-19 are similar, and the ratio may be a ratio between the PWM parameter and the rotation rate (in RPM) of the corresponding fan. Figure 2 The technique used to calculate the ratio is described in detail in .

[0045] In some embodiments, at least two of the fans 16-19 (e.g., fans 16 and 17) may be different from each other. Therefore, the ratio between the PWM parameter and the rotational speed may be different between fans 16 and 17 and is monitored in each of the fans 16-19. It is worth noting that a deviation from the ratio between PWM and RPM indicates that there is an error in the corresponding fan.

[0046] In some embodiments, if the RPM and PWM do not match in a given fan, the controller is configured to (i) notify the user that the given fan has failed and, if necessary, (ii) adjust the PWM applied by driver 33 to other fans to compensate for the failure of the given fan.

[0047] In some embodiments, the above process is iterative so that in response to changes in the measured temperature, the controller adjusts the corresponding PWM parameters and compares: (i) the PWM parameters calculated in all thermal zones, and (ii) the calculated maximum PWM parameters with the PWM parameters applied by the current PWM signal. If the calculated maximum PWM parameters are greater than the PWM parameters applied by the current PWM signal, the controller is configured to adjust the PWM signal by applying the calculated maximum PWM parameters to the cooling device (e.g., fans 16-19).

[0048] For example, if the temperature in ASIC 20 (measured by sensor 24) increases, for example, to about 80° C., the controller is configured to adjust the PWM parameters of the thermal zone with ASIC 20 to about 80%. At the same time, the temperature in processor 44 remains at about 70° C. In this example, the controller adjusts the maximum PWM parameter to 80%, and the PWM parameter calculates a modified PWM signal based on the maximum value of 80%. And the driver 33 applies the modified PWM signal to the fans 16-19.

[0049] In some embodiments, in response to applying the modified PWM signal, the speed (e.g., RPM) of the fans 16-19 is changed to control (e.g., reduce) the temperature of the thermal zone having the ASIC 20 and other thermal zones. For example, (i) the speed of one or more fans can be increased to reduce the temperature of one or more corresponding thermal zones, or alternatively, (ii) the speed of one or more fans can be reduced, for example, to save power as long as the temperature of one or more corresponding thermal zones is within a specified temperature range. It is worth noting that the PWM adjustment is performed as part of the temperature and power consumption optimization of the system 11.

[0050] In addition, in response to receiving a signal from sensor 24 indicating a decrease in temperature (e.g., to approximately 50° C.), the controller readjusts the PWM parameters of the thermal zones having ASIC 20, identifies the maximum PWM parameter among all thermal zones, compares the maximum PWM parameter to the 80% PWM parameter, and, if applicable, generates another revised version of the PWM signal, which the driver applies to fans 16-19.

[0051] It is noted that in this example, all cooling devices include fans, but in other embodiments, at least one cooling device of system 11 may include a pump (not shown) configured to flow a cooling fluid to cool at least one thermal zone (i.e., location) in system 11. In such embodiments, the parameter may include a flow rate of the cooling fluid, and the controller is configured to calculate a ratio between the flow rate and a corresponding PWM parameter intended to be driven into the pump by driver 33.

[0052] In some embodiments, PSU 66 and PSU fan 77 may be controlled using separate controllers (referred to herein as given controllers) and may receive PWM signals from another driver (not shown). It is worth noting that in order to prevent or at least reduce turbulence within system 11, the flow rate of air moved by the rotation of PSU fan 77 must be equal to or higher than the maximum flow rate of air moved by each of fans 16-19. Therefore, the rotation speed of PSU fan 77 is generally equal to or higher than the rotation speed of each of fans 16-19.

[0053] In some embodiments, in response to identifying that the PWM parameters of the PSU fan 77 are less than the maximum PWM parameters applied to the fans 16-19 (i.e., less than the PWM parameters required by the system 11), the controller of the system 11 (implemented in the processor 44 as described above) is configured to override the given controller. Therefore, the controller of the system 11 is configured to calculate a modified PWM signal intended to be applied to the PSU fan 77. The modified PWM signal is similar to or greater than the maximum PWM parameters calculated for the system 11, thereby preventing turbulence in the air flowing within the system 11.

[0054] The above technology is implemented in the following Figure 2 Described in more detail in .

[0055] Figure 2 is a block diagram 88 schematically illustrating monitoring and controlling the temperature of components in the switch system 11 according to one embodiment of the present invention.

[0056] In some embodiments, block diagram 88 includes: (i) a set of monitoring blocks, referred to herein as monitors 40, (ii) a set of control blocks, referred to herein as control devices (control) 50, and (iii) applying a PWM signal (e.g., using (one or more) drivers 33) to a cooling device (e.g., fans 16-19).

[0057] In some embodiments, monitor 40 includes a telemetry unit 45 configured to receive: (i) temperature data from blocks 41 and 43 and from ASIC 20, and (ii) status of cooling devices (e.g., fans 16-19) from block 46, as will be described in more detail below. In this example, telemetry unit 45 may be implemented in interface 55 and / or processor 44, while block 46 may be implemented in a controller implemented in processor 44.

[0058] In some embodiments, the data received from blocks 41 and 43 and ASIC 20 includes temperature data of (a) EOTR 10, (b) ASIC 20, (c) power regulator (DCDC), (d) processor 44 and interface 55, (e) DDR 21, and (f) CB 32, which are received from sensors 23, 24, 25, 26, 27, and 28, respectively, as described above. Figure 1 In this example, ASIC 20 receives temperature data from one or more sensors 23, 25-28 from block 41, adds the temperature data received from sensor 24, and sends the data to telemetry unit 45. In addition, or alternatively, telemetry unit 45 receives temperature data from one or more sensors 23, 25-28 directly from block 43.

[0059] In some embodiments, the controller is configured to apply algorithms to optimize the effects of power, noise, and other parameters of cooling devices (e.g., fans and / or fluid pumps) as a function of the temperature of key devices (e.g., ASICs 20 and processors 44) of the system 11. Thus, in configuration data block 47, the controller is configured to, among other things, determine a list of components (e.g., devices), and based on signals received from temperature sensors (indicative of temperature readings in various components), the controller is configured to output a specific behavior of the cooling device for each state of the monitored devices and cooling devices.

[0060] In some embodiments, for each device in system 11 having a heat sink for dissipating the heat generated by the respective device, it is expected that the cooling effect will be slower than the change in airflow rate. Therefore, assume that ASIC 20 is configured to provide its own monitored temperature to the controller using a specific frequency bandwidth (about 0.1 Hz in this example or any other suitable frequency).

[0061] Reference is now made to the control device 50. In some embodiments, the control device 50 includes a thermal algorithm manager block 48, which in this example is implemented in the controller and is configured to receive temperature and fan 16-19 status data as described above from the telemetry unit 45. It should be noted that the data received from the telemetry unit 45 is affected by the parameters received from the configuration data block 47. In this example, the data from the telemetry unit 45 is received via the Management Component Transport Protocol (MCTP) or using any other suitable type of protocol.

[0062] In some embodiments, based on data received from telemetry unit 45, thermal algorithm manager block 48 is configured to: (i) convert temperature measurements into PWM parameters, and (ii) generate one or more PWM signals constituting cooling targets for each of the thermal zones described above based on the PWM parameters and additional inputs (e.g., one or more errors in components of system 11 described below).

[0063] In some embodiments, the controller is configured to select a maximum PWM parameter among the above PWM parameters and apply the maximum PWM parameter to a common PWM signal intended to be applied to all fans 16-19, as described above. Figure 1 Alternatively, the controller is configured to calculate multiple PWM signals intended to be applied to multiple types of cooling devices (eg, fans or pumps), respectively.

[0064] In some embodiments, in a block 51 implemented in a driver 33, one or more drivers 33 are configured to: (i) receive a PWM signal from a controller, and (ii) drive the PWM signal to a block 52 indicating a cooling device of the system 11. In a general example, the system 11 includes n types of blocks 52a-52n (i.e., different types of cooling devices), and one or more drivers 33 are configured to: (i) drive a PWM signal with a maximum PWM parameter to two or more (e.g., all) blocks 52a-52n, or (ii) drive different PWM signals based on different PWM parameters, as described above. In this example, the block 52a includes fans 16-19, and the PWM signal applied to the fans 16-19 is based on the maximum PWM parameter among the calculated PWM parameters. The calculation of the PWM parameters is described in detail below.

[0065] In some embodiments, when the management of the monitor 40 and the control device 50 implemented by software and / or firmware is unavailable (e.g., during software startup or software suspension), the hardware (e.g., the driver 33) should control the cooling device (e.g., fan) in the worst case. Therefore, the driver 33 drives the fan to the maximum cooling level.

[0066] In some embodiments, during initialization of the cooling device, the controller is configured to run one loop of the algorithm (described below) and perform PWM parameter settings after the initialization phase. It is worth noting that in order to prevent an undesired throttling state or undefined values ​​before obtaining temperature and speed data from the system, the controller controls the cooling device (e.g., fans 16-19) only after the initialization phase.

[0067] In some embodiments, the controller is configured to receive a signal indicating a rotational speed of each fan, and based on the PWM parameters and the rotational speed, the controller is configured to determine a characteristic of each fan. Note that at least one of the fans 16-19 operates from a predefined PWM, also referred to herein as a minimum PWM parameter. In addition, each of the fans 16-19 has a minimum rotational speed level (e.g., measured in RPM), and therefore, the calculation of the ratio between PWM and RPM assumes that RPMs below the minimum PWM level are equal to the minimum level of RPM. In addition, the calculation of the slope of the linear line (PWM versus RPM) assumes that the average slope is calculated only for RPMs obtained at PWM parameter levels greater than the minimum PWM level.

[0068] In some embodiments, the controller is configured to calculate the PWM for each thermal zone (e.g., component) of the system 11 using the following parameters:

[0069] T sensor Represents the components (e.g., ASIC 20, processor 44, and above) Figure 1 The temperature read by the temperature sensor (other components described in

[0070] T min represents the minimum temperature of each component,

[0071] T max Indicates the maximum temperature allowed for each component,

[0072] PWM min Indicates the minimum percentage (%) of PWM for each component,

[0073] PWM max Indicates the maximum percentage (%) of PWM for each component.

[0074] In such embodiments, the controller is configured to calculate the PWM (in %) of each component using the following conditional flow:

[0075] (a) If T sensor Less than T Min , then PWM is equal to PWM min ,

[0076] (b) If T sensor Greater than T Max , then PWM is equal to PWM Max ,as well as

[0077] (c) If T sensor Between T Min To T Max If the PWM parameters are between , then equation (i) is used to calculate the values ​​of the PWM parameters:

[0078] (i)

[0079] It is worth noting that the output of equation (i) provides continuous values ​​of the PWM parameters that take into account temperature changes, and the controller can react as a proportional-integral-derivative (PID) controller while preserving T Max PWM Max Value and T min PWM min value.

[0080] In some embodiments, the PWM parameters are represented using a 255-bit register, so the representation of the calculated PWM in the 255-bit register is provided by equation (ii):

[0081] (ii)

[0082] Where PWM reg Represents the calculated PWM in a 255-bit register.

[0083] In some embodiments, the setting of PWM parameters takes into account errors that may occur in various components of the system. Errors and PWM settings (both with and without errors) are described in detail below.

[0084] In some embodiments, block 46 receives a signal from a fan tachometer (not shown) of fan 16-19 indicating the speed (e.g., RPM) of fan 16-19, which is responsive to the PWM parameters driven to fan 16-19 by one or more drivers 33. It is worth noting that each of fans 16-19 can reach predefined minimum and maximum speed levels, referred to herein as RPM, respectively. min and RPM max .

[0085] In some embodiments, based on the applied PWM parameters and the corresponding RPM data received from the tachometer, the controller is configured to calculate an average of the linear slopes for each of the fans 16-19. In addition, the controller is configured to calculate the fan PWM tolerance for each of the fans 16-19 using equation (iii):

[0086] (iii)y=m*x+b

[0087] in,

[0088] y represents the RPM measured by the fan tachometer,

[0089] m represents the average slope between PWM and RPM,

[0090] x represents the PWM applied by driver 33, and

[0091] b represents a constant, which is calculated as described below.

[0092] In some embodiments, the controller is configured to calculate the average slope of the ratio between PWM and RPM using the following conditional flow:

[0093] For each PWM level, denoted PWM[i],

[0094] If PWM[i] <PWM min

[0095] isValid[i]=0

[0096] Where isValid[i] represents the validity factor of PWM[i].

[0097] In other words, if the value of PWM[i] is less than PWM minIf the value of PWM[i] is not used to calculate the slope of the ratio between PWM and RPM, the corresponding PWM[i] will not be used to calculate the slope of the ratio between PWM and RPM. Therefore, the effectiveness factor (as shown below) is given a value of zero.

[0098] In some embodiments, if the value of PWM[i] is greater than PWM min If the value of isValid[i] is equal to 1, the corresponding PWM[i] will be used to calculate the slope of the ratio between PWM and RPM (ie, the validity factor isValid[i] = 1).

[0099] In some embodiments, the average slope is calculated by calculating the slope of each instance [i] multiplied by a validity factor, which yields a value of 1 (when valid) or 0 (when invalid). Thus, the average slope (averageSlope) is calculated using formula (iv):

[0100] (iv)

[0101] Slope a [i] represents the slope at each instance [i].

[0102] In some embodiments, the controller is configured to calculate the constant "b" using equation (v):

[0103] (v) b = RPM max -AverageSlope*PWM max

[0104] In such an embodiment, the controller is configured to calculate the speed (eg, RPM) of each of the fans 16-19 using the following conditional flow:

[0105] If the value of the PWM parameter is less than the minimum value of PWM (PWM min ), the RPM level is set to the minimum RPM level (RMM min ),otherwise

[0106] The controller is configured to calculate RPM using equation (vi):

[0107] (iv)RPM=AverageSlope*PWM+b

[0108] Table (A) shown below shows an example of PWM parameter values, measured rotation speed, calculated slope, effectiveness factor and calculated rotation speed of a device:

[0109]

[0110] Table A: Examples of PWM parameters, measured RPM, calculated slope, effectiveness factor, and calculated RPM.

[0111] Error Detection and Impact on Thermal Management

[0112] Various types of errors and failures may occur during operation of the switch system 11. For example, errors in one or more of the following: PSU fan 77, fans 16-19 and / or the above-mentioned fluid pumps (in the case of fluid-based cooling), and errors in temperature readings performed by sensors 23-28.

[0113] In some embodiments, the controller is configured to dynamically update the data and parameters of Table (A) above and maintain a thermal management protocol in response to detecting at least the errors described in detail below (and optionally other scenarios).

[0114] Errors in the PSU fans 77 may include (i) one or more PSU fans 77 being missing (eg, one or more PSU fans 77 were incorrectly replaced during maintenance), and (ii) one or more PSU fans 77 being unable to operate.

[0115] Errors in one or more fans 16-19 may include (i) one or more fans 16-19 being missing (e.g., one or more of the fans were incorrectly replaced during maintenance), (ii) one or more fans are installed in the opposite direction, causing air to flow in the opposite direction to that required, and (iii) errors in the ratio between the calculated PWM and the rotational speed of the fans 16-19.

[0116] It should be noted that the system 11 can allow airflow in a single direction, or airflow in two directions. In addition, each fan has an indication of the direction of airflow, for example, pushing air into the system 11, or extracting air from the system 11.

[0117] In some embodiments, a direction indication for each of fans 16-19 and 77 is stored in system 11, such as in a register in processor 44. In other words, the intended direction of airflow (eg, push or pull air) is stored.

[0118] In some embodiments, in the case of a single airflow direction, the controller implemented in the processor 44 is configured to detect the actual direction of the airflow. In one embodiment, the actual airflow direction can be detected by installing an additional ambient temperature sensor 28 (e.g., between the panel 12 and the ASIC 20 (or at any other suitable location in the system 11) and comparing the temperature readings received from the two sensors 28. Thus, the lower temperature reading indicates the upstream direction of the airflow. In addition, or alternatively, the direction of the airflow can be obtained using a suitable airflow sensor.

[0119] In some embodiments, in the case of unidirectional or bidirectional airflow, the controller compares for each fan whether the actual direction of the airflow is similar to the expected direction. If there is a difference between the actual direction and the expected direction, the controller is configured to identify an error in the actual direction of the airflow. In such an embodiment, if permitted by the operator of the system 11, the controller is configured to initiate corrective action in the corresponding fan. Alternatively, the controller is configured to adjust the calculation of the PWM based on the error identified in the actual direction of the airflow.

[0120] In some embodiments, the controller is configured to: (i) define a frequency of temperature measurements for each temperature sensor located in each thermal zone, and (ii) detect a fault in the temperature readings, for example, by receiving one or more expected temperature readings not at the predefined frequency. In addition, extreme temperature readings that deviate significantly from predefined control limits for thermal management in the system 11 (e.g., stored in the processor 44) may also indicate a fault in the temperature readings (but may also indicate actual overheating in the corresponding thermal zone if the temperature slightly exceeds the control limits). In some embodiments, upon retrying to receive a new temperature reading, the controller is configured to apply a temperature reading based on one or more of the most recent valid temperature readings received from the corresponding temperature sensor. Figure 1 and Figure 2 The technique described in .

[0121] In some embodiments, the controller is configured to maintain one or more criteria for defining a fault in the temperature readings. For example, the criteria include three consecutive faults in the temperature readings from the same temperature sensor.

[0122] In some embodiments, all of the above errors, as well as other errors related to thermal management of the system 11, are logged and can be used by the controller to adjust parameters related to PWM, fan speed, and other parameters shown in Table (A) above.

[0123] In some cases, an event may occur that the controller is unfamiliar with, or for which the controller does not have an appropriate thermal management protocol stored. In some embodiments, in response to identifying one or more of the above events, the controller is configured to set all fans of the system 11 (e.g., fans 16-19) to their maximum speed. In addition, in response to an error in the temperature reading from the ambient sensor 28, the controller is configured to set a predefined maximum ambient temperature and calculate the PWM and other parameters shown in the above table (A) based on the predefined maximum ambient temperature.

[0124] In some cases, additional temperature sensors may be coupled to the EOTR 10. In some cases, the signals received from these sensors may indicate: (i) an error in the temperature readings, and / or (ii) overheating of the AOC. In some embodiments, the controller may not use the data received from these sensors to adjust parameters related to thermal management of the system 11 when performing thermal management of the system 11. It is worth noting that such AOCs are easily replaceable, and localized overheating of a particular AOC may occur due to a localized fault in the AOC that is unrelated to the operation of the system 11.

[0125] In alternative embodiments, any other suitable processing device and software and / or firmware may be used instead of or in addition to a controller to perform thermal management in system 11. For example, at least some of the above-described thermal management techniques may be performed using firmware running on ASIC 20, or using any other entity including suitable devices and software and / or firmware.

[0126] In some embodiments, the controller is configured to adjust the PWM, for example, in response to changes in temperature readings, as described above. In addition, the controller is configured to maintain one or more thresholds that indicate the fastest allowable rate of reduction of the PWM to avoid vibration of the fan of the system 11, which is detrimental to the stability of the fan, and other undesirable phenomena, such as noise generated by the fan.

[0127] Figure 3 is a flow chart schematically illustrating a method for monitoring and controlling the temperature of components of the switch system 11 according to an embodiment of the present invention.

[0128] The method begins with a component definition step 100, in which a plurality of thermal control components (e.g., ASIC 20, processor 44, and above) located in a plurality of locations are defined. Figure 1 4 and other components described in the description, which are also referred to herein as thermal zones of the electronic system 11. It is worth noting that the definition of thermal control components can be performed by a designer and / or user of the system 11, but the list can also be defined by a controller implemented in the processor 44 or any other suitable component of the system 11.

[0129] In the polling time definition step 102, the controller defines the temperature measurement frequency of each thermal zone, as described above. Figure 1 and Figure 2 Described in detail in .

[0130] In a measurement receiving step 104, the interface 55 receives a plurality of measurements of a plurality of corresponding temperatures from one or more of the sensors 23-28 located in the hot zone, as described above. Figure 1 and Figure 2It is worth noting that the temperature is measured based on the predefined thermal control component list and measurement frequency defined in steps 100 and 102 above.

[0131] In a conversion step 106, the controller checks whether one or more errors have occurred in one or more of: (i) the temperature readings of the temperature sensors, and (ii) one or more cooling devices (e.g., fans 16-19 and PSU fan 77). In some embodiments, the controller converts the plurality of measurements into a plurality of PWM parameters. It is noted that the controller is configured to adjust the PWM parameters in response to detecting the occurrence of any of the above errors, as described above. Figure 1 and Figure 2 Described in detail in .

[0132] In the PWM parameter selection step 108, the controller selects the maximum PWM parameter from the multiple PWM parameters in the above step 102, as described above. Figure 1 and Figure 2 In alternative embodiments, the controller may select PWM parameters in addition to or instead of the maximum PWM parameters.

[0133] In the signal calculation step 110, the controller calculates one or more PWM signals based on at least the maximum PWM parameters. In some embodiments, the controller is configured to calculate the PWM signals based on additional parameters, such as different types of cooling devices (e.g., different types of fans and pumps configured to flow cooling fluid to cool the hot zone). In alternative embodiments, the controller is configured to set the PWM parameters in step 106 based on the temperature readings, and subsequently (e.g., in step 110), the controller is configured to adjust the PWM signals in response to an error occurring in at least one temperature sensor and / or cooling device (e.g., any of the aforementioned fans 16-19) of the switch system 11.

[0134] In a temperature control step 112 concluding the method, the TMC 22 is configured to control a plurality of temperatures in a plurality of temperature zones by applying one or more calculated PWM signals to one or more cooling devices using one or more drivers 33. In one embodiment, the controller calculates the PWM signal based on the maximum PWM parameter, and the driver 33 applies the calculated PWM signal to the fans 16-19, as described above. Figure 1 and Figure 2 Described in detail in .

[0135] Figure 3 The method is simplified for conceptual clarity, and additional sub-steps (such as but not limited to calculating the correlation between the PWM parameters and the speed of the corresponding fan) have been described above. Figure 1 and Figure 2 In addition, Figure 3 The method is based on a specific configuration of a switch system 11 shown by way of example in order to illustrate certain problems solved by embodiments of the present disclosure and to demonstrate the application of these embodiments in enhancing the performance of such switch systems. However, the embodiments of the present disclosure and their variations are by no means limited to this particular type of example switch system, and the principles described herein can be similarly applied to other types of electronic systems with any suitable thermal management requirements.

[0136] It should be understood that the above embodiments are cited by way of example, and the present invention is not limited to the contents specifically shown and described above. On the contrary, the scope of the present invention includes combinations and sub-combinations of the various features described above, as well as variants and modifications that would occur to a person skilled in the art when reading the above description and that are not disclosed in the prior art. The documents cited in this patent application should be considered as an integral part of this application, but if the definition of any term in these cited documents conflicts with the explicit or implicit definition in this specification, only the definition in this specification should be considered.

Claims

1. A device comprising: An interface for receiving a plurality of measurement values ​​of a plurality of temperatures respectively measured in a plurality of locations of the electronic system; as well as Thermal Management Circuit TMC for: Converting the plurality of measured values ​​into a plurality of pulse width modulation (PWM) parameters; calculating one or more PWM signals based at least on the plurality of PWM parameters; as well as The plurality of temperatures are controlled by applying the one or more PWM signals to one or more cooling devices.

2. The apparatus of claim 1, wherein the TMC is configured to: (i) select a maximum PWM parameter among the plurality of PWM parameters, and (ii) apply the maximum PWM parameter to all of the cooling devices.

3. The device according to claim 1, wherein the TMC is used to select a list of two or more components located at two or more of the locations, and the device includes two or more temperature sensors respectively coupled to the components to respectively perform measurements of the temperatures in the components in the list.

4. The apparatus of claim 3 , wherein the interface is to receive an error signal indicating an error in at least one of: (i) the one or more cooling devices, and (ii) one or more of the temperature sensors, and wherein the TMC is to adjust at least one of the PWM signals in response to the error.

5. The apparatus according to claim 3, wherein the plurality of temperature sensors include a first temperature sensor and a second temperature sensor to respectively perform a first measurement and a second measurement of the plurality of measurements, and wherein, The TMC includes a controller for: (i) defining, for the first temperature sensor, a first frequency for the first measurement, and (ii) defining, for the second temperature sensor, a second frequency for the second measurement, the second frequency being different from the first frequency.

6. The apparatus of claim 1, wherein the TMC comprises a controller for calculating ratios between the plurality of PWM parameters and a plurality of parameters of the one or more cooling devices.

7. The apparatus of claim 6, wherein at least one of the cooling devices comprises a fan, wherein At least one parameter of the plurality of parameters comprises a rotational speed of the fan, and wherein the controller is configured to calculate a ratio between the rotational speed of the fan and a corresponding PWM parameter of the plurality of PWM parameters.

8. The apparatus according to claim 7 comprises (i) a plurality of fans respectively controlled to operate at a plurality of rotational speeds, (ii) a plurality of components located in at least some of the plurality of locations, and (iii) a power supply unit (PSU) for supplying power to at least some of the plurality of components, wherein the PSU comprises a PSU fan, and wherein the TMC is used to set a given rotational speed of the PSU fan to be equal to or greater than a maximum value of the plurality of rotational speeds.

9. The apparatus of claim 7, wherein the controller is configured to control a rotational direction of the fan, wherein the plurality of measurements include two or more given measurements indicative of ambient temperatures of the electronic system, and wherein the controller is configured to determine the rotational direction of the fan based on a minimum ambient temperature among the ambient temperatures.

10. The apparatus of claim 6, wherein at least one of the cooling devices comprises a pump for flowing a cooling fluid to cool at least one of the plurality of locations, wherein at least one of the plurality of parameters comprises a flow rate of the cooling fluid, and wherein the controller is for calculating the ratio between the flow rate of the cooling fluid and a corresponding PWM parameter of the plurality of PWM parameters.

11. A method comprising: receiving a plurality of measurement values ​​of a plurality of temperatures measured in a plurality of locations of the electronic system, respectively; Converting the plurality of measured values ​​into a plurality of pulse width modulation (PWM) parameters; calculating one or more PWM signals based at least on the plurality of PWM parameters; as well as The plurality of temperatures are controlled by applying the one or more PWM signals to one or more cooling devices.

12. The method of claim 11 , wherein calculating the one or more PWM signals comprises: A maximum PWM parameter among the plurality of PWM parameters is selected, and wherein applying the one or more PWM signals includes applying the maximum PWM parameter to all of the cooling devices.

13. The method according to claim 11, comprising: A list of two or more components located at two or more of the locations is selected, and measured values ​​of temperatures in the components on the list are received from two or more temperature sensors coupled to the components, respectively.

14. The method according to claim 13, comprising: An error signal is received indicating an error in at least one of: (i) the one or more cooling devices, and (ii) one or more of the temperature sensors, and at least one of the PWM signals is adjusted in response to the error.

15. The method of claim 13, wherein receiving a plurality of measurements comprises: A first measurement value and a second measurement value are received from a first temperature sensor and a second temperature sensor of the two or more temperature sensors, respectively, and include: (i) for the first temperature sensor, defining a first frequency of the first measurement value, and (ii) for the second temperature sensor, defining a second frequency of the second measurement value, the second frequency being different from the first frequency.

16. The method of claim 11, wherein calculating the one or more PWM signals comprises: Ratios between the plurality of PWM parameters and a plurality of parameters of the one or more cooling devices are calculated.

17. The method of claim 16, wherein at least one of the cooling devices comprises a fan, wherein at least one of the plurality of parameters comprises a rotational speed of the fan, and wherein calculating the ratio comprises: A ratio between a rotation speed of the fan and a corresponding PWM parameter among the plurality of PWM parameters is calculated.

18. The method according to claim 17, comprising: (i) a plurality of fans each controlled to operate at a plurality of rotational speeds, (ii) a plurality of components located in at least some of the plurality of locations, and (iii) a power supply unit (PSU) for supplying power to at least some of the plurality of components, wherein the PSU includes a PSU fan, and wherein controlling the plurality of temperatures includes setting a given rotational speed of the PSU fan to be equal to or greater than a maximum value of the plurality of rotational speeds.

19. The method of claim 17, wherein controlling the plurality of temperatures comprises: Controlling a rotational direction of the fan, wherein receiving the plurality of measurements comprises receiving two or more given measurements indicative of ambient temperatures of the electronic system, and wherein controlling the rotational direction comprises determining the rotational direction of the fan based on a minimum ambient temperature among the ambient temperatures.

20. The method of claim 16, wherein at least one of the cooling devices comprises a pump for flowing a cooling fluid to cool at least one of the plurality of locations, wherein at least one of the plurality of parameters comprises a flow rate of the cooling fluid, and wherein calculating the ratio comprises calculating the ratio between the flow rate of the cooling fluid and a corresponding PWM parameter of the plurality of PWM parameters.

21. The method of claim 11, wherein calculating the one or more PWM signals comprises: A PWM parameter from among the plurality of PWM parameters that satisfies a predetermined condition is selected, and wherein applying the one or more PWM signals comprises applying the selected PWM parameter to all of the cooling devices.

Images