The present application claims priority to European Patent Appl. No. 22306240.7, filed Aug. 18, 2022 entitled “Immersion-Cooled Electronic Device and Cooling Monitoring System for Immersion Cooled Electronic Device”, the entirety of which is incorporated herein by reference; and to European Patent Appl. No. 22306276.1 filed Aug. 29, 2022 entitled “Detection and Deflection of Fluid Leakages in Immersion Cooling Systems”, the entirety of which is incorporated by reference herein.
The present technology relates to immersion-cooled electronic equipment. In particular, the present technology relates to detection of anomalies in cooling of an immersion-cooled electronic device.
Electronic equipment, for example servers, memory banks, computer disks, and the like, is conventionally grouped in equipment racks. Large data centers and other large computing facilities may contain thousands of racks supporting thousands or even tens of thousands of servers. The racks, including equipment mounted in their backplanes, consume large amounts of electric power and generate significant amounts of heat. Cooling needs are important in such racks. Some electronic devices, such as processors, generate so much heat that they could fail within seconds in case of a lack of cooling.
Liquid cooling, in particular water cooling, has been used as an addition or replacement to traditional forced-air cooling. Cold plates, for example water blocks having internal channels for channelized water circulation, may be mounted on heat-generating components, such as processors, to displace heat from the processors toward heat exchangers. Immersion cooling (sometimes called immersive cooling) has also recently gained traction. Electronic components are inserted in a container that is fully or partially filled with a non-conducting cooling liquid, for example an oil-based dielectric cooling liquid. Efficient thermal contact is obtained between the electronic components and the dielectric cooling liquid. Immersion cooling systems commonly take the form of large tanks in which the electronic devices are submerged. Hybrid cooling systems involving both water cooling and immersion cooling have recently been introduced.
However, such cooling systems may not be efficient enough to remove enough thermal energy from the electronic device and/or may be prone to malfunctions (e.g. leakage of water within the dielectric cooling liquid). As such, a system for monitoring the cooling systems of an immersion-cooled electronic device may be desirable.
The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches.
Embodiments of the present technology have been developed based on developers' appreciation of shortcomings associated with the prior art. In particular, such shortcomings may include the difficulty of detecting leaks of a channelized liquid, such as is used in water blocks, into the dielectric cooling liquid in a cooling system that uses both water blocks (or other liquid-cooled cold plates), and by immersion cooling.
In accordance with a first broad aspect of the present disclosure, there is provided an electronic device receiving electric power from a power supply, the electronic device comprising a board at least in part immersed in an immersion case comprising a first heat-transfer liquid for cooling of the electronic device; one or more sensors configured to measure an operating parameter of the first heat-transfer liquid; and a controller communicably connected to the one or more sensors, the controller being configured to receive signals from the one or more sensors and, in response to determining that the signals indicate that the operating parameter of the first heat-transfer liquid is above a threshold, cause to disconnect the electronic device from the power supply.
In some embodiments of the electronic device, the one or more sensors are anomaly sensors that transmit a fault signal to the controller in response to detecting that the operating parameter of the first heat-transfer liquid is above the threshold; and the controller causes to disconnect the electronic device from the power supply in response to receiving the fault signal.
In some embodiments of the electronic device, the one or more sensors transmit measurement signals for the operating parameter of the first heat-transfer liquid to the controller. Determining, by the controller, that the signals indicate that the operating parameter of the first heat-transfer liquid is above the threshold comprises comparing, by the controller, measurement values carried in the measurement signals with the threshold.
In some embodiments of the electronic device, the one or more sensors comprises a leak detection arrangement disposed in a bottom portion of the board; the leak detection arrangement determines a presence of a second heat-transfer liquid in a bottom portion of the immersion case; and the second heat-transfer liquid has a density that is higher than a density of the first heat-transfer liquid.
In some embodiments of the electronic device, the second heat-transfer liquid comprises water; the leak detection arrangement comprises a conductivity sensor; and the leak detection arrangement transmits the fault signal in response to detecting the conductivity being above a pre-determined conductivity threshold.
In some embodiments of the electronic device, the conductivity sensor comprises a plurality of conductivity sensors disposed one above another along a gravity axis; and the controller determines a fill rate of the second heat-transfer liquid within the immersion case based on fault signals transmitted by two or more of the conductivity sensors.
In some embodiments of the electronic device, the controller is further configured to, in response to determining the fill rate, trigger a counter indicative of an amount of time that has passed since the fill rate has been determined; and, in response to the counter reaching a first pre-determined count value, cause to disconnect the electronic device from the power supply, the first pre-determined count value being based on the determined fill rate.
In some embodiments of the electronic device, the second heat-transfer liquid has a pH that is different from a pH of the first heat-transfer liquid; and the leak detection arrangement comprises a pH sensor.
In some embodiments of the cooling monitoring system, the second heat-transfer liquid comprises water and glycol.
In some embodiments of the electronic device, the one or more sensors comprise a temperature sensor configured to determine a temperature of the first heat-transfer liquid.
In some embodiments of the electronic device, the temperature sensor is mounted on the board such that, in use, the temperature is proximate to a surface of the first heat-transfer liquid.
In some embodiments of the electronic device, the temperature sensor is configured to transmit a fault signal in response to detecting a temperature of the first heat-transfer liquid being above a first pre-determined temperature threshold.
In some embodiments of the electronic device, the controller is further configured to, in response to the temperature sensor determining that the temperature of the first heat-transfer liquid has reached a second pre-determined temperature threshold, trigger a counter indicative of an amount of time that has passed since the temperature of the first heat-transfer liquid has reached the second pre-determined temperature threshold; and, in response to the counter reaching a second pre-determined count value, cause to disconnect the electronic device from the power supply.
In some embodiments of the electronic device, the controller is further configured to, subsequent to triggering the counter indicative of an amount of time that has passed since the temperature of the first heat-transfer liquid has reached the second pre-determined temperature threshold, in response to the counter reaching a third pre-determined count value, transmit an alert signal to an operator device communicably connected thereto to indicate occurrence of an anomaly to an operator of the electronic device.
In some embodiments of the electronic device, the controller is communicably connected to a power distribution unit (PDU) distributing electric power from the power supply to the electronic device, the controller being configured to cause to disconnect the electronic device from the PDU.
In some embodiments of the electronic device, the first heat-transfer liquid is a dielectric liquid.
In some embodiments of the electronic device, the operating parameter is selected from a group of operating parameters comprising: a temperature, a conductivity, a viscosity and a density of the first heat-transfer liquid.
In accordance with a second broad aspect of the present disclosure, there is provided a cooling monitoring system for an electronic device receiving power from a power supply, the electronic device comprising a board being at least in part immersed in a immersion case comprising a first heat-transfer liquid for cooling of the electronic device. The cooling monitoring system comprises one or more sensors configured to measure an operating parameter of the first heat-transfer liquid, a controller communicably connected to the one or more sensors, the controller being configured to receive signals from the one or more sensors and, in response to determining that the signals indicate that the operating parameter of the first heat-transfer liquid is above a threshold, cause to disconnect the electronic device from the power supply.
In some embodiments of the cooling monitoring system, the one or more sensors are anomaly sensors that transmit a fault signal to the controller in response to detecting that the operating parameter of the first heat-transfer liquid is above the threshold; and the controller causes to disconnect the electronic device from the power supply in response to receiving the fault signal.
In some embodiments of the cooling monitoring system, the one or more sensors transmit measurement signals for the operating parameter of the first heat-transfer liquid to the controller; and determining, by the controller, that the signals indicate that the operating parameter of the first heat-transfer liquid is above the threshold comprises comparing, by the controller, measurement values carried in the measurement signals with the threshold.
In some embodiments of the cooling monitoring system, the one or more sensors comprises a leak detection arrangement disposed in a bottom portion of the board, the leak detection arrangement is configured to determine a presence of a second heat-transfer liquid in a bottom portion of the immersion case, the second heat-transfer liquid has a density that is higher than a density of the first heat-transfer liquid.
In some embodiments of the cooling monitoring system, the second heat-transfer liquid is water; the leak detection arrangement comprises a conductivity sensor; and the leak detection arrangement is configured to transmit a fault signal in response to detecting the conductivity being above a pre-determined conductivity threshold.
In some embodiments of the cooling monitoring system, the conductivity sensor comprises a plurality of conductivity sensors disposed one above another along a gravity axis; the controller is configured to determine a fill rate of the water within the immersion case based on fault signals transmitted by two or more of the conductivity sensors.
In some embodiments of the cooling monitoring system, the controller is further configured to, in response to determining the fill rate, trigger a counter indicative of an amount of time that has passed since the fill rate has been determined, in response to the counter reaching a first pre-determined count value, cause to disconnect the electronic device from the power supply, the first pre-determined count value being based on the determined fill rate.
In some embodiments of the cooling monitoring system, the second heat-transfer liquid has a pH that is different from a pH of the first heat-transfer liquid; and the leak detection arrangement comprises a pH sensor.
In some embodiments of the cooling monitoring system, the second heat-transfer liquid comprises water and glycol.
In some embodiments of the cooling monitoring system, the one or more sensors comprise a temperature sensor configured to determine a temperature of the first heat-transfer liquid.
In some embodiments of the cooling monitoring system, the temperature sensor is mounted the board such that, in use the temperature is proximate to a surface of the heat-transfer liquid.
In some embodiments of the cooling monitoring system, the temperature sensor is configured to transmit a fault signal in response to detecting a temperature of the heat-transfer liquid being above a first pre-determined temperature threshold.
In some embodiments of the cooling monitoring system, the controller is further configured to trigger a counter indicative of an amount of time that has passed since the temperature of the heat-transfer liquid has reached a second pre-determined temperature threshold; in response to the counter reaching a second pre-determined count value, cause to disconnect the electronic device from the power supply
In some embodiments of the cooling monitoring system, the controller is further configured to, subsequent to triggering the counter indicative of an amount of time that has passed since the temperature of the first heat-transfer liquid has reached the second pre-determined temperature threshold, in response to the counter reaching a third pre-determined count value, transmit an alert signal to an operator device communicably connected thereto to indicate occurrence of an anomaly to an operator of the electronic device.
In some embodiments of the cooling monitoring system, the controller is communicably connected to a power distribution unit (PDU) distributing electric power from the power supply to the electronic device, the controller being configured to cause to disconnect the electronic device from the PDU.
In the context of the present specification, unless expressly provided otherwise, a computer system may refer, but is not limited to, an “electronic device”, an “operation system”, a “system”, a “computer-based system”, a “controller unit”, a “monitoring device”, a “control device” and/or any combination thereof appropriate to the relevant task at hand.
In the context of the present specification, unless expressly provided otherwise, the expression “computer-readable medium” and “memory” are intended to include media of any nature and kind whatsoever, non-limiting examples of which include RAM, ROM, disks (CD-ROMs, DVDs, floppy disks, hard disk drives, etc.), USB keys, flash memory cards, solid state-drives, and tape drives. Still in the context of the present specification, “a” computer-readable medium and “the” computer-readable medium should not be construed as being the same computer-readable medium. To the contrary, and whenever appropriate, “a” computer-readable medium and “the” computer-readable medium may also be construed as a first computer-readable medium and a second computer-readable medium.
In the context of the present specification, unless expressly provided otherwise, the words “first”, “second”, “third”, etc. have been used as adjectives only for the purpose of allowing for distinction between the nouns that they modify from one another, and not for the purpose of describing any particular relationship between those nouns.
Implementations of the present technology each have at least one of the above-mentioned object and/or aspects, but do not necessarily have all of them. It should be understood that some aspects of the present technology that have resulted from attempting to attain the above-mentioned object may not satisfy this object and/or may satisfy other objects not specifically recited herein.
Additional and/or alternative features, aspects and advantages of implementations of the present technology will become apparent from the following description, the accompanying drawings and the appended claims.
These and other features, aspects and advantages of the present technology will become better understood with regard to the following description, appended claims and accompanying drawings where:
It should also be noted that, unless otherwise explicitly specified herein, the drawings are not to scale.
The examples and conditional language recited herein are principally intended to aid the reader in understanding the principles of the present technology and not to limit its scope to such specifically recited examples and conditions. It will be appreciated that those skilled in the art may devise various arrangements that, although not explicitly described or shown herein, nonetheless embody the principles of the present technology.
Furthermore, as an aid to understanding, the following description may describe relatively simplified implementations of the present technology. As persons skilled in the art would understand, various implementations of the present technology may be of a greater complexity.
In some cases, what are believed to be helpful examples of modifications to the present technology may also be set forth. This is done merely as an aid to understanding, and, again, not to define the scope or set forth the bounds of the present technology. These modifications are not an exhaustive list, and a person skilled in the art may make other modifications while nonetheless remaining within the scope of the present technology. Further, where no examples of modifications have been set forth, it should not be interpreted that no modifications are possible and/or that what is described is the sole manner of implementing that element of the present technology.
Moreover, all statements herein reciting principles, aspects, and implementations of the present technology, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof, whether they are currently known or developed in the future. Thus, for example, it will be appreciated by those skilled in the art that any block diagrams herein represents conceptual views of illustrative systems embodying the principles of the present technology.
With these fundamentals in place, we will now consider some non-limiting examples to illustrate various implementations of aspects of the present disclosure.
In this embodiment, each electronic device 120 is electrically connected to a corresponding PDU 110 over a switching device 310 (e.g. a Solid State Relay). The switching device 310 is selectively closed or open to respectively disconnect and connect the electronic device 120 to the PDU 110. Operation of the switching device 310 is performed by a controller 500 (see
Each PDU 110 includes an input connector for receiving electric power from a power supply (e.g. AC power supply). The power supply may be a monophasic power supply or a multi-phasic power supply. The input connector may be, for example and without limitation, a CEE 7-type plug for use in European countries. Each PDU 110 further includes a plurality of output connectors for electrically connecting a plurality of corresponding electronic devices 120 via the switching devices 310. The output connectors may be, for example and without limitations, C13-type plugs. In some embodiments, each PDU 110 includes eight (8) output connectors.
It is contemplated that the electronic devices 120 may generate a significant amount of heat. Consequently, the rack system 100 may use a cooling system to cool down the electronic devices 120 to prevent the electronic devices 120 from being damaged. In this embodiment, the cooling system is a hybrid cooling system including an immersion cooling system and a channelized cooling system.
As used herein, an immersion cooling system is a cooling system in which the electronic device is in direct contact with a non-conductive (dielectric) cooling liquid, which either flows over at least portions of the electronic device, or in which at least portions of the electronic device are submerged. For example, in the rack-mounted assembly 104, the immersion case 116 may contain a dielectric immersion cooling liquid (not shown in
In some embodiments, the immersion case 116 may also include structures or devices for cooling the dielectric cooling liquid. For example, a convection-inducing structure, such as a serpentine convection coil 124 in which a flow of cooling liquid (e.g. water) is maintained may be used to cool the dielectric cooling liquid via natural convection. Alternatively or additionally, a pump (not shown) may be used to circulate the dielectric cooling liquid either within the immersion case 116 or through an external cooling system (not shown). In some embodiments, a two-phase system in which dielectric cooling liquid in a gaseous phase is cooled by condensation may be used. Generally, any technology or combination for cooling the dielectric cooling liquid may be used without departing from the principles disclosed herein. The serpentine convection coil 124 may be omitted or replaced with other convection-inducing structures or devices for circulating the dielectric immersion cooling liquid in some embodiments.
As used herein, a channelized cooling system is a cooling system in which heat-generating components of the electronic device 120 (i.e. the electronic components 122) are cooled using one or more liquid cooling units 250, which may also be called “cold plates” or “water blocks” (although a liquid circulating through the “water blocks” may be any of a wide variety of known thermal transfer liquids, rather than water). Liquid connections of the liquid cooling units 250 are described in greater details herein after. Examples of heat-generating components that may be cooled using such a thermal transfer devices include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), neural processing units (NPUs), tensor processing units (TPUs), power supply circuitry, and application specific integrated circuits (ASICs), including, for example, ASICs configured for high-speed cryptocurrency mining. The present disclosure describes a cooling monitoring system that detect anomalies of the cooling of the electronic device 120 and that may disconnect the electronic device 120 from its corresponding power supply in response to detecting an anomaly.
The electronic device 120 includes one or more electronic components 122 (only one of which is illustrated for clarity of the
Additionally, the electronic device 120 is also cooled by the channelized cooling system that circulates a channelized cooling liquid, or a “second heat-transfer liquid”, through one or more liquid cooling units 250 (only one of which is illustrated for clarity of the
The liquid cooling unit 250 may for example include a liquid inlet 252 fluidly connected to the liquid cooling inlet conduit 106 of the rack 100 (
In this embodiment, the liquid cooling unit 250 is also submerged within the heat-transfer liquid 315. The serpentine convection coil 124 introduced in the description of
After absorbing heat from the electronic device 120 and from the heat-transfer liquid 315, the heated channelized cooling liquid is conveyed through a heat exchanger system (not shown), the operation of which will generally be familiar to those of skill in the art. The heat exchanger system cools the channelized cooling fluid, which may then be recirculated to the rack system 100 through a channelized cooling loop.
It will be understood that there may be many additional features, combinations, and variations of such hybrid cooling systems combining channelized liquid cooling and immersion cooling of the electronic device 120. In some embodiments, multiple electronic devices, similar to the electronic device 120, may be immersed in a single immersion case or an immersion tank.
Other variations may involve changing the order of the components and/or the serpentine convection coil in the channelized cooling loop. For example, the channelized cooling fluid may flow through the serpentine convection coil after flowing through the liquid cooling unit 250. In some embodiments, the serpentine convection coil may be part of a different channelized cooling loop than the liquid cooling units 250. These variations and additional features may be used in various combinations, and may be used in connection with the embodiments described above, or other embodiments.
The cooling monitoring system 400 includes the controller 500 and one or more sensors communicably connected to the controller 500. In an embodiment, the sensors transmit measurement signals for the operating parameter of the heat-transfer liquid 315 to the controller 500. The controller 500 further determines that the measurement signals indicate that the operating parameter of the heat-transfer liquid 315 is above the threshold by comparing measurement values carried in the measurement signals with the threshold.
In another embodiment, the sensors transmit a fault signal to the controller 500 in response to detecting that the operating parameter of the heat-transfer liquid 315 is above the threshold. The controller 500 further cause to disconnect the electronic device 120 from the power supply in response to receiving the fault signal. In this embodiment, the sensors may thus be referred to as “anomaly sensors”.
Operating parameters that are measured by the sensors may be a temperature, a conductivity, a viscosity, a density, and/or any other physical or chemical characteristics of the heat-transfer liquid 315.
As shown in
In an embodiment, the switching device 310 may be integrated in the electronic device 120. In other embodiments, the switching device 310 may be located outside the electronic device 120 (e.g. along a power line that transmits electric power from the PDU 110 to the electronic device 120).
As has been discussed above, hybrid cooling systems for electronic devices 120 may include both immersion cooling systems, in which the electronic devices are immersed or submerged in a dielectric immersion cooling liquid, and channelized cooling systems, in which heat transfer devices such as water blocks are used to cool components of the electronic device, using a liquid that flows through channels between and within the heat transfer devices.
In some cases, the same liquid may be used as both the dielectric immersion cooling liquid and the channelized cooling liquid (i.e., the liquid that flows through the water blocks). However, in some systems, the characteristics of the dielectric immersion cooling liquid and/or the cost of the dielectric immersion cooling liquid may render it inappropriate for use in the channelized cooling system. Often, the channelized cooling liquid will be water, or some other liquid that provides appropriate heat transfer characteristics for the channelized cooling system, but may not be usable for immersion cooling, e.g., due to its conductivity or due to corrosion or other damage that it may cause to components of the electronic device. For example, if water is used as the channelized cooling liquid, it is likely that the concentration of ions in the water will cause the water to be sufficiently conductive to cause damage to electronic components. Even if the water is initially provided as distilled or deionized water, the concentration of ions will increase as the water is circulated through the channelized cooling system.
To avoid damage to immersed or submerged electronic devices, it is desirable to determine whether channelized cooling liquid is leaking into the dielectric immersion cooling liquid. Dielectric immersion cooling liquids are typically either hydrocarbon- or fluorocarbon-based and typically have densities that are lower than the density of water. If the channelized cooling liquid has a higher density than the dielectric immersion cooling liquid, which will typically be the case, then the channelized cooling fluid eventually leaking into the immersion cooling liquid will sink to a bottom portion of the immersion case.
In accordance with various embodiments of the disclosure, a leak detection arrangement, such as a sensor, may be installed in a bottom portion of the immersion case 116 of each rack-mounted assembly 104 (or in a bottom portion of any part of the rack system 100 where the dielectric cooling liquid may flow) to detect the presence of the channelized cooling liquid, which would indicate that there is a leak in the channelized cooling system. Generally, this bottom portion of the immersion case 116 should be far enough below any immersed or submerged electronic device 120 that, absent a major leak, the channelized cooling fluid will not collect around any components of the electronic device 120. Once the fluid is detected, an alarm may be raised, or an operator may otherwise be informed of the immersion case 116 in which the leak was detected so that remedial measures may be taken.
In an embodiment, the sensors include a leak detection arrangement 600 communicably connected to the controller 500 and adapted to determine a presence of the second heat-transfer liquid in a bottom portion of the immersion case 116. More specifically, the second heat-transfer liquid used for liquid cooling of the electronic device 120 is selected to have a density that is higher than a density of the heat-transfer liquid 315. As a result, in case of leakage of the second heat-transfer liquid within the immersion case 116, the second heat-transfer liquid sinks to the bottom of the immersion case 116. In this embodiment, in order to detect a presence of the second heat-transfer liquid in the immersion case 116, the leak detection arrangement 600 is disposed in a bottom portion of the board 118. Broadly speaking, the leak detection arrangement 600 may include any sensor adapted to measure a temperature, a conductivity, a viscosity, a density, and/or any other physical or chemical characteristics of the heat-transfer liquid 315.
In an embodiment, the leak detection arrangement 600 includes one or more conductivity sensors 605 for determining a conductivity of a fluid at the bottom portion of the board 118. In this embodiment, the second heat-transfer liquid is water. As a result, the conductivity sensors 605 are expected to determine a conductivity value that is non-null, or at least a variation of the measured conductivity value, in response to some of the second heat-transfer liquid having leaked to the bottom portion of the immersion case 116.
In an embodiment, the leak detection arrangement 600 transmits measurement signals including information about a measured conductivity of the heat-transfer liquid 315 to the controller 500. The controller 500 further determines that the measurement signals indicate that the conductivity of the heat-transfer liquid 315 is above the threshold by comparing measurement values carried in the measurement signals with the pre-determined conductivity threshold.
In another embodiment, the leak detection arrangement 600 transmits a fault signal to the controller 500 in response to determining that a real measured conductivity is above a pre-determined conductivity threshold. In some embodiments, value of the pre-determined conductivity threshold is stored in a memory of the controller 500 and the leak detection arrangement 600 transmits data including information about the real measured conductivity. The controller 500 then compares the real measured conductivity to the pre-determined conductivity threshold. In response to the real measured conductivity being greater than the pre-determined conductivity threshold, the controller 500 may open the switching device 310.
In this embodiment, the leak detection arrangement 600 includes a plurality of conductivity sensors 605 disposed one above another along a gravity axis, each conductivity sensor 605 being communicably connected to the controller 500. In use, a fill rate of the second heat-transfer liquid in the immersive case 116 may be determined based on conductivity values measured by the conductivity sensors 605. More specifically, as the second heat-transfer liquid leaks from the channelized cooling loop 260, a bottommost conductivity sensor 605 may first transmit a fault signal to the controller 500. Later in time as the second heat-transfer liquid continues to leak from the channelized cooling loop 260 and fills the immersion case 116, a second conductivity sensor 605, adjacent and above the bottommost conductivity sensor 605 along the gravity axis, may further transmit a second fault signal to the controller 500 upon measuring a conductivity value above the pre-determined conductivity threshold. Alternatively, the
A fill rate and temporal evolution thereof may thus be determined based on times of reception of the different fault signals from the respective conductivity sensors 605. In some embodiments, the controller 500 further triggers, in response to determining the fill rate, a counter 502 indicative of an amount of time that has passed since the fill rate has been determined. In response to the counter 502 reaching a first pre-determined count value, the controller 500 may cause to disconnect the electronic device 120 from the power supply. More specifically, once the counter 502 reaches the first pre-determined count value, the controller 500 may open the switching device 310 to disconnect from the PDU 110 and from the power supply. In some embodiments, in response to the counter 502 reaching a second pre-determined count value, the controller 500 may transmit an alert signal to an operator device communicably connected thereto to indicate occurrence of an anomaly to an operator of the datacenter. The second pre-determined count value may be smaller than the first pre-determined count value. There may be a higher number of pre-determined count values and associated alert signals in alternative embodiments.
In some embodiments, the pre-determined count value is based on the determined fill rate. For example, the pre-determined count value associated with fill rate determined to be between 0.1 L per hour and 0.4 L per hour may be 30 minutes. The pre-determined count value associated with fill rate determined to be between 0.4 L per hour and 0.8 L per hour may be 10 minutes. The controller 500 may thus disconnect the electronic device 120 from the power supply before the leaking channelized cooling liquid reaches sensitive components of the electronic device 120 (e.g. the electronic components 122).
In an embodiment, the cooling monitoring system 400 further includes a temperature sensor 320. The temperature sensor 320 measures a temperature of the heat-transfer liquid 315, a vapor thereof and/or air located at a top portion of the immersion case 116. The temperature sensor 320 may be located near a top of the heat-transfer liquid 315, as shown on
In some embodiment, the controller 500 may trigger a new parallel instance of the counter 502 upon receiving the fault signal from the temperature sensor 320. In response to the counter reaching a third pre-determined count value, the controller 500 may cause to disconnect the electronic device 120 from the power supply. More specifically, once the counter 502 reaches the third pre-determined count value, the controller 500 may open the switching device 310 to disconnect the electronic device 120 from the PDU 110 and from the power supply. In some embodiments, in response to the counter 502 reaching a fourth pre-determined count value, the controller 500 may transmit an alert signal to an operator device communicably connected thereto to indicate occurrence of an anomaly to an operator of the datacenter. The fourth pre-determined count value may be smaller than the first pre-determined count value.
In a given rack system (e.g. the rack system 100), selective disconnection of the electronic devices 120 from the power supply by the corresponding controllers 500 facilitates operation of the electronic devices 120 in case an anomaly is detected. Indeed, if a faulty cooling system is detected by a corresponding cooling monitoring system 400, the corresponding electronic device 120 is disconnected from the power supply without impacting operation of the other electronic devices 120 in other rack-mounted assemblies 104 of the rack system 100. For example, propagation of potential damages of a short-circuit occurring in a given electronic device 120 (e.g. server) of the datacenter is limited by individual disconnection of the servers from the power supply.
In some embodiments, the controller 500 is communicably connected with an operator interface (not shown) of the datacenter (e.g. a control room of the datacenter) and transmits, in response to determining occurrence of an anomaly, a second fault signal to the operator including information about the faulty electronic device 120 in which the cooling monitoring system 400 has detected an anomaly (e.g. leaking channelized cooling liquid). Said information may include, without limitation, an identification of the faulty electronic device 120 and data provided by the sensors.
In some embodiments, the controller 500 is communicably connected with a valve (e.g. a solenoid valve) located in the channelized cooling loop 260 upstream the serpentine convection coil 124 and the liquid cooling unit 250, external to the immersion case 116. In response to determining occurrence of an anomaly, the controller 500 also closes the valve in order to limit damages to the electronic device 120.
The dielectric immersion cooling liquid 315 has very low conductivity. Thus, when there has been no leak, there will be low conductivity (or high resistivity) between the electrodes 820 and 822. In the example shown in
It will be understood by those of ordinary skill in the art that many variations on a system that uses conductivity or resistivity measurement to detect the presence of the channelized cooling liquid may be used. For example, the electrodes 820 and 822 may be disposed within a single unit or holder of a given conductivity sensor 605 that is open to liquid, and that holds the electrodes 820 and 822 at a predetermined distance from each other. In some embodiments, such a holder may be configured to be mounted in the immersion case 116 through a “standardized” opening in the bottom portion of the immersion case 116, which is configured to receive any of a variety of sensors or other leak detection arrangements for determining the presence of the channelized cooling liquid in the bottom portion of the immersion case 116.
In the illustrative embodiment of
The dielectric immersion cooling liquid 315 and the channelized cooling liquid may have different pH values. The liquids may be selected to have this characteristic, or the pH may be measurably different simply due to chemical differences between the two liquids. In the example shown in
As with other embodiments, it will be understood by those of ordinary skill in the art that many variations on a system that uses pH measurements to detect the presence of the channelized cooling liquid may be used. For example, the pH sensor may be configured to be mounted in the immersion case through a “standardized” opening in the bottom portion of the immersion case, which is configured to receive any of a variety of sensors or other leak detection arrangements for determining the presence of the channelized cooling liquid in the bottom portion of the immersion case.
As an example,
The controller 500 is operatively connected, via the input/output interface 520, to the leak detection arrangement 600, the switching device 310 and the temperature sensor 320. The controller 500 executes the code instructions 532 stored in the memory device 530 to implement the various above-described functions that may be present in a particular embodiment.
Even though the controller 500 is depicted as a separate entity on
It is to be understood that the operations and functionality of the described cooling monitoring system 400, its constituent components, and associated processes may be achieved by any one or more of hardware-based, software-based, and firmware-based elements. Such operational alternatives do not, in any way, limit the scope of the present disclosure.
In some embodiments, the cooling monitoring system 400 are part of the electronic device 120. More specifically, the electronic device 120 may include the sensors (i.e. the leak detection arrangement 600 and the temperature sensor 320) mounted on the board 118 of the electronic device 120 and communicably connected to the electronic device 120, the functions of the controller 500 being performed by the electronic device 120.
It will be understood that, although the embodiments presented herein have been described with reference to specific features and structures, various modifications and combinations may be made without departing from the disclosure. For example, it is contemplated that in some embodiments, two or more of the leak detection arrangements described above may be used, in any combination. For instance, an embodiment may use a combination of a pH sensor and a conductivity sensor to detect leaks, and may also include a valve to permit manual testing and draining of leaked channelized cooling liquid. The specification and drawings are, accordingly, to be regarded simply as an illustration of the discussed implementations or embodiments and their principles as defined by the appended claims, and are contemplated to cover any and all modifications, variations, combinations or equivalents that fall within the scope of the present disclosure.
It is contemplated that the electronic device 120 and the cooling monitoring system 100 can be represented as presented, in accordance with some non-limiting implementations of the present technology, in the following numbered clauses.
CLAUSE 1. An electronic device receiving electric power from a power supply, the electronic device comprising:
in response to the counter reaching a third pre-determined count value, transmit an alert signal to an operator device communicably connected thereto to indicate occurrence of an anomaly to an operator of the electronic device.
CLAUSE 15. The electronic device of any one of clauses 1 to 14, wherein the controller is communicably connected to a power distribution unit (PDU) distributing electric power from the power supply to the electronic device, the controller being configured to cause to disconnect the electronic device from the PDU.
CLAUSE 16. The electronic device of any one of clauses 1 to 15, wherein the first heat-transfer liquid is a dielectric liquid.
CLAUSE 17. The electronic device of any one of clauses 1 to 16, wherein the operating parameter is selected from a group of operating parameters comprising: a temperature, a conductivity, a viscosity and a density of the first heat-transfer liquid.
CLAUSE 18. A cooling monitoring system for an electronic device receiving power from a power supply, the electronic device comprising a board being at least in part immersed in a immersion case comprising a first heat-transfer liquid for cooling of the electronic device, the cooling monitoring system comprising:
Modifications and improvements to the above-described implementations of the present technology may become apparent to those skilled in the art. The foregoing description is intended to be exemplary rather than limiting. The scope of the present technology is therefore intended to be limited solely by the scope of the appended claims.
Number | Date | Country | Kind |
---|---|---|---|
22306240.7 | Aug 2022 | EP | regional |
22306276.1 | Aug 2022 | EP | regional |