341 results about "Slow-start" patented technology

A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session. The method uses the Layer 7 content from a previous session as an estimate to help select the server and uses a default priority to scheduling the transmitting of the handshaking packets. Updated Layer 7 content available after the handshaking phase is then used to reset the priority for the transmit schedule and becomes available for use in load balancing of the next TCP session.

A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session. The method uses the Layer 7 content from a previous session as an estimate to help select the server and uses a default priority to scheduling the transmitting of the handshaking packets. Updated Layer 7 content available after the handshaking phase is then used to reset the priority for the transmit schedule and becomes available for use in load balancing of the next TCP session.

Methods, apparatuses and systems directed to improving the efficiency of bandwidth allocation schemes by adapting to slow-start mechanisms associated with network communications protocols, such as the TCP / IP protocol suite. In one implementation, the present invention scales down the initial target rate assigned to a data flow to a fraction of an initial estimate of the effective rate capacity of the communications path between two hosts. As packets are received, the target rate is gradually increased, eventually up to the detected rate capacity of the communications path. Implementations of the present invention improve the efficiency of bandwidth allocation by reducing the over-allocation of bandwidth to data flows during the slow-start phase, leaving more bandwidth available to other data flows.

In a TCP / IP network, congestion control techniques such as slow start and congestion avoidance are employed. Such networks include wired and wireless links. However, normal operation of the wireless links exhibit different latencies than those exhibited over the wired link. The protocols employed in the wired network do not lend themselves well to efficient communication over wireless connections, and can cause slow start to be triggered. Determining when a sender will timeout due to non-receipt of an ACK, and intervening with a suppression message having an advertised window of zero to pause the user, are employed to prevent congestion control mechanisms such as slow start and congestion avoidance from activation

A method and equipment for accelerating throughput of communication segments from a sender (30) to a receiver (40) each of which include a protocol layer (30a 40a) for providing such segments, the method in case of TCP including a first step (20a) in which the sender protocol layer (30a) initializes a congestion window (cwnd) to some initial size (iwnd) and increases the congestion window by one segment each time it receives an ACK, but upon receiving an indication of low congestion, performs a step (20c) of accelerated start in which it sets a slow start threshold (SSTHRES) to a standard initial value (typically 65535) and re-initializes cwnd to a new value, and the sender protocol layer (30a) then increments cwnd at one or another predetermined rate—depending on whether the start immediately follows a new connection or instead follows a transfer of an existing connection to a new path—in respect to received ACKs.

The fast dynamic measurement of bandwidth in a TCP network environment utilizes a single pair of packets to calculate bandwidth between two entities on a network (such as the Internet). This calculation is based upon the packet-pair technique. This bandwidth measurement is extremely quick. On its journey across a network, communication devices may delay the packet pairs. In particular, TCP networks have two algorithms designed to delay some packets with the goal of increasing the overall throughput of the network. However, these algorithms effectively delay a packet pair designed to measure bandwidth. Therefore, they distort the measurement. These algorithms are Nagle and Slow Start. The fast dynamic measurement of bandwidth implements countermeasures to overcome the delays imposed by these algorithms. Such countermeasures include disabling the application of the Nagle Algorithm; minimizing the buffering of packets by sending a “push” packet right after the packet pair; and avoiding the Slow Start Algorithm by priming it with a dummy packet.

A system and method for efficiently forwarding client requests from a proxy server in a TCP / IP computing environment is described. A plurality of transient requests are received from individual sending clients into a request queue. Each request is commonly addressed to an origin server. Time estimates of TCP overhead, slow start overhead, time-to-idle, and request transfer time for sending the requests over each of a plurality of managed connections to the origin server are dynamically calculated, concurrent to receiving and during processing of each request. The managed connection is chosen from, in order of preferred selection, a warm idle connection, an active connection with a time-to-idle less than a slow start overhead, a cold idle connection, an active connection with a time-to-idle less than a TCP overhead, a new managed connection, and an existing managed connection with a smallest time-to-idle. Each request is forwarded to the origin server over the selected managed connection.

In the preferred embodiments, it is first determined whether or not a TCP connection from a sending device to a receiving device in the wireless communications network is in a slow start phase. If the TCP connection is in a slow start phase, then the data to be sent in the TCP connection that is allocated a priority that is higher than the priority allocated to other data to be sent by the sending device. The sending device may be a Serving GPRS Support Node (SGSN), a device in a Radio Access Network (RAN) or other network device, and the method of the preferred embodiments may be implemented by software installed and executed on the network device.

The invention provides a direct-current power supply hot plug slow starting control circuit, which comprises a discrete component slow starting circuit, power resistance circuits and a metal oxide semiconductor (MOS) tube drain-source electrode detecting circuit. The power resistance circuits are connected in parallel between MOS tube drain-source electrodes and a drain electrode of the discrete component slow starting circuit. The MOS tube drain-source electrode detecting circuit is connected with the power resistance circuits and the discrete component slow starting circuit and used for detecting voltage values of the power resistance circuits. When the voltage values are in a range of set values, MOS tubes of the power resistance circuits are connected. When the voltage values are beyond the range of set values, the MOS tubes of the power resistance circuits are disconnected. The invention further provides a control method for direct-current power supply hot plug slow starting. The direct-current power supply hot plug slow starting control circuit and the control method can effectively avoid MOS breakdown due to avalanche, simultaneously can effectively reduce voltage stress of the MOS tube drain-source electrodes and facilitates economic selection.

Methods and apparatus are described for intelligently assigning a portion of a cluster's traffic (e.g., buckets) to a cache system to minimize overloading of such cache system. In general terms, when a new cache system enters a cache cluster and / or starts up, the new cache system's full bucket allocation is not immediately assigned to the new cache system. Instead, only a portion of the full bucket allocation is initially assigned to the new cache system. In one embodiment, the new cache system's bucket assignment is gradually increased until the cache system is handling it's full bucket allocation or it becomes overloaded. The cache system's load is also checked periodically to determine whether it has become overloaded. When the cache system becomes overloaded, buckets are immediately shed from the cache system. In sum, the new cache system's load is adjusted until it is handling an optimum number of buckets.

The invention relates to a variable-frequency power source based on the control of a digital signal processor, which comprises a switch power source module, a control circuit, a circuit for isolating and shaping pulse-width modulating signal, IPM inverting circuits, a circuit for detecting and protecting busbar voltage, a rectification input slow-start circuit, a communication circuit, an interface circuit for isolating and inputting parallel signals and an human-computer interface circuit for displaying the key. The invention adopts the structure of a single digital signal processor (DSP) coupled with the double IPM inverting circuits, provides two paths of independent variable-frequency power sources for two sets of asynchronous motors at the same time and carries out independent speed regulations to the two sets of asynchronous motors. The variable-frequency power source of the invention has the advantages of small volume, low power consumption, high reliability and being convenient for bulk production, etc., and adopts an appropriate switch frequency and an advanced voltage space vector pulse width modulation algorithm (SVPWM), thereby lowering the noise during the operation of the asynchronous motors and increasing the voltage utilization rate, with obvious effect on energy saving.

A first loss determination section 13 of a first communication device 10 determines that a data unit is lost if an acknowledgment response for the transmitted data unit from a second communication device 30 is not received within a predetermined time and retransmits the data unit when the determination is made. When a determination section 16 determines that a spurious timeout has occurred, a window control section 17 sets a target value for decreasing the size of a congestion window and then gradually decreases the size of the congestion window to the target value when the acknowledgment response is received. Therefore, in a case of executing a response algorithm for changing a slow start threshold and the congestion window, if a segment loss occurs subsequent to the spurious timeout, an efficient loss recovery is achieved and the throughput is improved.

The invention relates to a pervasive service-oriented adaptive network congestion control method. The method comprises the following steps that: a source node for transmitting information measures round-trip time (RTT) of a target node for receiving the information, wherein when the ratio CSRTT of the latest measuring value to the minimum of the historical RTT is increased, the congestion is caused by too many packets forming a line in an intermediate network node; the target node distinguishes the received data packet is a normal data packet or is a packet-pair used for detecting bandwidth and feeds the estimated available bandwidth back to the source node; according to a feedback signal, the source node distinguishes the congestion states with four levels according to a preset rule and uses the four congestion states as a basis of speed adjustment; when a new connection exists, the target node transmits three repeated acknowledge characters (ACK) of the last received data before switching; and the source node resets a slow start threshold by using the result after receiving an acknowledgment packet which is not data bursting one window, but data for only transmitting two back-to-back packets to detect the available bandwidth on a new path.

An embodiment of a system and method that uses inline measurements to probe available bandwidth for a transmission control protocol, and adaptively sets a slow-start threshold according to the available bandwidth. The method includes initializing a congestion window “cwnd,” sending cwnd packets, estimating an available bandwidth for the cwnd packets. The congestion window cwnd is set to a higher number, and the higher number of further packets is sent if the available bandwidth is greater than a first threshold level. The available bandwidth is re-estimated for the higher number of the further packets, and a soft start threshold “ssthresh” is set to the re-estimated available bandwidth. A statistical measure is calculated for the re-estimated available bandwidth, and the congestion window cwnd is set equal to ssthresh if a ratio of the statistical measure to the re-estimated available bandwidth is less than a second threshold level.

A novel approach is provided for avoiding the “slow-start restart” in TCP communications when network conditions dictate such. The disclosed approach serves to overcome the latency related to the “slow-start restart” by assessing network conditions and avoiding the “slow-start restart” when network conditions justify the avoidance. The disclosed methods, applications and devices implement the periodic communication of a probe packet that is generated and transmitted from a TCP sender to a TCP receiver during the period that the TCP network connection remains idle. Receipt of the probe packet by the TCP receiver will trigger transmission of an acknowledgment message by the TCP receiver. Upon receipt of the acknowledgement message the TCP sender will restart measurement of the idleness period and, as such the “slow-start restart” is avoided.

A plurality of network characteristics of a wireless network are determined and a plurality of TCP session parameters are updated. The network characteristics may be determined based at least in part on a comparison of the estimated bandwidth and estimated propagation delay of the wireless network and the typical bandwidths and propagation delays of one or more wireless networks. The TCP session parameters may be updated based at least in part on the network characteristics. The TCP session parameters may be used to limit the congestion window, retransmission timeout and slow start threshold.

Some embodiments provide a forwarding element that inspects the size of each of several packets in a data flow to determine whether the data flow is an elephant flow. The forwarding element inspects the size because, in order for the packet to be of a certain size, the data flow had to already have gone through a slow start in which smaller packets are transferred and by definition be an elephant flow. When the forwarding element receives a packet in a data flow, the forwarding element identifies the size of the packet. The forwarding element then determines if the size of the packet is greater than a threshold size. If the size is greater, the forwarding element specifies that the packet's data flow is an elephant flow.

A transport layer protocol such as the Stream Control Transmission Protocol uses a new traffic control technique instead of the TCP slow start algorithm. The procedure assumes that the network on which it is implemented has a fixed bandwidth assigned for the connection, and that the allotted bandwidth roughly matches the traffic load. Based on this, under message loss conditions it is only necessary to ensure that signaling traffic emitted into the network by the sender is no greater than the fixed bandwidth that has been allocated to the connection. That is, retransmissions take bandwidth away from a fixed allocation that has been made for the connection, but do not cause the connection itself to reduce the overall traffic it generates into the network; rather, it maintains the same traffic level. This technique prevents congestion in the network from increasing when message loss occurs; at the same time it does not reduce bandwidth for the association as rapidly as the slow start procedure.

In a TCP / IP network, congestion control techniques such as slow start and congestion avoidance are employed. Such networks include wired and wireless links. However, normal operation of the wireless links exhibit different latencies than those exhibited over the wired link. The protocols employed in the wired network do not lend themselves well to efficient communication over wireless connections, and can cause slow start to be triggered. Determining when a sender will timeout due to non-receipt of an ACK, and intervening with a suppression message having an advertised window of zero to pause the user, are employed to prevent congestion control mechanisms such as slow start and congestion avoidance from activation.

The invention discloses a direct current power supply slow starting circuit of a gateway device, and belongs to a power supply control circuit. The direct current power supply slow starting circuit comprises an anti-shake module and a conduction control tube. The anti-shake module is connected with a power adapter and the conduction control tube respectively, and the conduction control tube is connected with the gateway device and is a PMOS tube. The anti-shake module is connected with the grid electrode and the source electrode of the PMOS tube respectively, and the drain electrode of the PMOS tube is connected with the gateway device. The anti-shake module comprises a first resistor, a second resistor, a first capacitor and a second capacitor. A first divider resistor, the first capacitor and the second capacitor are connected in parallel, one end of a parallel end is connected with the power adapter and the source electrode of the PMOS tube respectively, and the other end of the parallel end is connected with the ground through a second divider resistor. The direct current power supply slow starting circuit has the advantages that the circuit is constructed by discrete passive devices, cost is low, the circuit can be restored and acted many times, delay protection time is more effective, and the circuit can bear larger instant impact currents which are loaded by the household gateway device.

The congestion in a network can be avoided by effectively utilizing a prepared network band even in a network where reception intervals of acknowledgments are not correct. According to the information about Ack or Sack (selective acknowledgment) received in a time of the minimum value of an RTT (rtt_min), the number of bytes of received segments (rcv_bytes) for which a receiving side acknowledges the reception is counted, and a received byte number setting unit 16 sets a congestion window (CWND) or a slow start threshold (SSTHRESH) when a packet loss occurs according to the number of bytes of received segments (rcv_bytes) counted by a received byte number counting unit 14 when a packet loss is detected by a loss detection unit 15.

The invention belongs to the technical field of air conditioner variable frequency motor control, and provides a dual-mode start control method and system of a compressor of a direct-current variable frequency air conditioner. The method includes: judging whether system pressure of the variable frequency air conditioner is balanced or not, if so, controlling the compressor to enter a high-frequency quick start mode, and if not, controlling the compressor to enter a normal slow start mode. Therefore, the compressor is guaranteed to be started quickly only when the system pressure is balanced, and start failure and demagnetization of the compressor due to the fact that the system pressure is unbalanced are avoided.

Systems and methods provide for controlling contention in a wireless network device. The systems and methods transmit a packet on a wireless network. If the transmission is not successful, then a contention window parameter is adjusted according to a fast backoff operation. If the packet transmission was successful and the current value of the contention window parameter is less than a threshold value then the contention window parameter is decreased according to a contention avoidance operation. If the packet transmission is successful and the current value of the contention window parameter is greater than the threshold value then the contention window parameter is decreased according to a slow start operation.

An inventive inverter has a semiconductor switch circuit connected to the primary winding of a transformer. The semiconductor switch circuit is respectively controlled by PWM to supply a constant current to the load connected to a secondary winding of the transformer. The inverter is capable of deliberately regulating its ac power output to the load and lowering the lower limit of the output power through control of the intermittent operation, in which an error signal for carrying out the PWM control is reduced to zero during each off-duty period. In addition, the error signal for the PWM control is slowly decreased or increased in each shift from an off-duty period to on-duty period, and vise versa, by charging or discharging the capacitor in a feedback circuit, thereby allowing slow start or slow end of the respective on-off operations for the constant current control through the PWM.

In the preferred embodiments, it is first determined whether or not a TCP connection from a sending device to a receiving device in the wireless communications network is in a slow start phase. If the TCP connection is in a slow start phase, then the data to be sent in the TCP connection that is allocated a priority that is higher than the priority allocated to other data to be sent by the sending device. The sending device may be a mobile terminal, a Serving GPRS Support Node (SGSN), a device in a WiMAX environment or other network device, and the method of the preferred embodiments may be implemented by software installed and executed on the network device.

A transport layer protocol such as the Stream Control Transmission Protocol uses a new traffic control technique instead of the TCP slow start algorithm. The procedure assumes that the network on which it is implemented has a fixed bandwidth assigned for the connection, and that the allotted bandwidth roughly matches the traffic load. Based on this, under message loss conditions it is only necessary to ensure that signaling traffic emitted into the network by the sender is no greater than the fixed bandwidth that has been allocated to the connection. That is, retransmissions take bandwidth away from a fixed allocation that has been made for the connection, but do not cause the connection itself to reduce the overall traffic it generates into the network; rather, it maintains the same traffic level. This technique prevents congestion in the network from increasing when message loss occurs; at the same time it does not reduce bandwidth for the association as rapidly as the slow start procedure.

The invention provides an electronic circuit breaker and a processing method thereof. The electronic circuit breaker and the processing method thereof realize delayed start and overcurrent protection functions by hardware circuits like a current sampling unit, a current limiting control unit, a slow start unit, a current comparing unit, a voltage sampling unit, a driving unit, an electronic switch and the like, so that various instability and delay problems caused by using a microprocessor for overcurrent protection can be avoided.

The invention discloses a direct current power supply input reverse irrigation prevention circuit and method. The circuit comprises a reverse connection prevention circuit, a soft start circuit and a sampling control circuit. The reverse connection prevention circuit comprises a reverse connection prevention metal oxide semiconductor field effect transistor MOSFET. The slow start circuit comprises a slow start MOSFET. The sampling control circuit samples voltage between the drain and the source of the slow start MOSFET. When the voltage between the drain and the source of the slow start MOSFET is less than the reference voltage, the reverse connection prevention MOSFET is controlled to switch off. According to the invention, current reverse irrigation is avoided when input short circuit occurs or input voltage rapidly drops; when a DC / DC converter uses a full bridge circuit, the increasing of the voltage stress of the secondary synchronous rectifier MOSFET drain and source of the converter and the damage of the MOSFET are avoided; when reverse lightning surge occurs in an input port, current reverse irrigation is avoided; and power supply output power-off caused by module input capacitor power-off is avoided.